论文检索

Deep Learning · Large Language Models

Bangji Yang, Hongbo Ma, Jiajun Fan, Ge Liu

Chain-of-Thought (CoT) reasoning has significantly improved the performance of Large Language Models (LLMs) but comes with substantial computational costs due to excessive token consumption. Existing approaches to reduce inference latency, such as explicit length penalties, often degrade reasoning quality by truncating necessary logical steps. In this work, we introduce a novel, SFT-free reinforcement learning framework that induces emergent token efficiency without explicit length constraints.We propose Batched Contextual Reinforcement (BCR), a training paradigm where the model is prompted to solve multiple reasoning tasks within a single context window, rewarded by independent instance-level accuracy. This formulation introduces an implicit information bottleneck: to maximize the cumulative reward within the context capacity, the model is forced to eliminate syntactic redundancy and focus attention on the semantic core of the reasoning path.Empirically, our method demonstrates a remarkable shift in the efficiency-accuracy Pareto frontier. Using a 1.5B parameter model JustRL-Deepseek-1.5B, we achieve **39.8--62.6% reduction in token usage** across five mathematical reasoning benchmarks while maintaining or improving accuracy on four of them. Most notably, on AMC23 and Minerva, we observe a ``free lunch'' phenomenon where accuracy improves by **+2.5%** and **+5.1%** respectively, despite using approximately **half the tokens**. Extensive ablation studies confirm that batched training acts as a superior form of implicit regularization that reduces hallucinations and sharpens attention. Our findings indicate that LLMs possess latent, high-density reasoning modes that can be unlocked via purely structural incentives in RL.

Reinforcement Learning · Deep RL

Guozheng Ma, Lu Li, Haoyu Wang, Zixuan Liu, Pierre-Luc Bacon, Dacheng Tao

Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded corrections. However, value learning in residual RL poses unique challenges that remain poorly understood. In this work, we identify two key bottlenecks: cold start pathology, where the critic lacks knowledge of the value landscape around the base policy, and structural scale mismatch, where the residual contribution is dwarfed by the base action. Through systematic investigation, we uncover the mechanisms underlying these bottlenecks, revealing that simple yet principled solutions suffice: base-policy transitions serve as an essential value anchor for implicit warmup, and critic normalization effectively restores representation sensitivity for discerning value differences. Based on these insights, we propose DAWN (Data-Anchored Warmup and Normalization), a minimal approach targeting efficient value learning in residual RL. By addressing these bottlenecks, DAWN demonstrates substantial efficiency gains across diverse benchmarks, policy architectures, and observation modalities.

Deep Learning · Large Language Models

Zhihao Dou, Qinjian Zhao, Zhongwei Wan, Zhang Dinggen, Weida Wang, Benteng Chen, Towsif Raiyan, Qingtao Pan, Yang Ouyang, Chaoda Song 等

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning. Existing methods, such as tree-based search and reinforcement learning (RL), attempt to address this issue but incur high computational costs and still struggle to produce reliable reasoning trajectories. To address these challenges, we propose Plan-Then-Action Enhanced Reasoning with Group Relative Policy Optimization (PTA-GRPO), a two-stage framework designed to jointly improve high-level planning and fine-grained CoT reasoning. Specifically, in the first stage, a given LLM is responsible for summarizing CoT reasoning into compact high-level guidance, which is then leveraged for supervised fine-tuning. Then, we introduce a guidance-aware reinforcement learning method that jointly optimizes the final output and the quality of guidance, enhancing reasoning effectiveness. We evaluate PTA-GRPO on ten reasoning benchmarks across mathematics and natural sciences, using five diverse base models spanning multiple data modalities. The results show that PTA-GRPO consistently delivers stable and significant improvements across models and tasks, demonstrating strong effectiveness and generalization.

Reinforcement Learning · Deep RL

Hai Zhong, Zhuoran Li, Xun Wang, Longbo Huang

Reparameterization Policy Gradient (RPG) has emerged as a powerful paradigm for model-based reinforcement learning, enabling high sample efficiency by backpropagating gradients through differentiable dynamics. However, prior RPG approaches have been predominantly restricted to Gaussian policies, limiting their performance and failing to leverage recent advances in generative models. In this work, we identify that flow policies, which generate actions via differentiable ODE integration, naturally align with the RPG framework, a connection not established in prior work. Yet, naively realizing this synergy is non-trivial: it often suffers from training instability and a lack of exploration. We propose Reparameterization Flow Policy Optimization (RFO). RFO computes policy gradients by backpropagating jointly through the flow generation process and system dynamics, unlocking high sample efficiency without requiring intractable log-likelihood calculations. RFO includes two tailored regularization terms for stability and exploration. We also propose a variant of RFO with action chunking. Extensive experiments on diverse locomotion and manipulation tasks—involving both rigid and soft bodies with state or visual inputs—demonstrate the effectiveness of RFO. Notably, on a challenging locomotion task controlling a soft-body quadruped, RFO achieves almost $2\times$ the reward of the state-of-the-art baseline.

Deep Learning · Large Language Models

Haixin Wang, Hejie Cui, Chenwei Zhang, Jiahui Gao, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun

Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse. We argue that this instability stems from inefficient exploration in multi-turn settings, where policies continue to generate low-information actions that neither reduce uncertainty nor advance task progress. To address this issue, we propose Token- and Turn-level Policy Optimization (T$^2$PO), an uncertainty-aware framework that explicitly controls exploration at fine-grained levels. At the token level, T$^2$PO monitors uncertainty dynamics and triggers a thinking intervention once the marginal uncertainty change falls below a threshold. At the turn level, T$^2$PO identifies interactions with negligible exploration progress and dynamically resamples such turns to avoid wasted rollouts. We evaluate T$^2$PO in diverse environments, including WebShop, ALFWorld, and Search QA, demonstrating substantial gains in training stability and performance improvements with better exploration efficiency. Code is available at https://anonymous.4open.science/r/T2PO-ICML-3C21.

Reinforcement Learning · Deep RL

Lingkai Kong, Anagha Satish, Hezi Jiang, Akseli Kangaslahti, Andrew Ma, Wenbo Chen, Mingxiao Song, Lily Xu, Milind Tambe

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced \emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility by design. Our method, LSFlow, learns a \emph{stochastic} policy in a compact continuous latent space via spherical flow matching, and delegates feasibility to a combinatorial optimization solver that maps each latent sample to a valid structured action. To improve efficiency, we train the value network directly in the latent space, avoiding repeated solver calls during policy optimization. To address the piecewise-constant and discontinuous value landscape induced by solver-based action selection, we introduce a smoothed Bellman operator that yields stable, well-defined learning targets. Empirically, our approach outperforms state-of-the-art baselines by an average of 20.6\% across a range of challenging combinatorial RL tasks.

Deep Learning · Generative Models and Autoencoders

Austin Xu, Xuan-Phi Nguyen, Yilun Zhou, Chien-Sheng Wu, Caiming Xiong, Shafiq Joty

Finetuning specialized generative evaluators has emerged as a popular paradigm to meet the increasing demand for scalable evaluation during both training and test-time. However, recent work has largely focused on applying new methodology, such as reinforcement learning (RL), to training evaluators, shying away from large-scale, data-driven development. In this work, we focus on data scaling, curating a set of 2.5M samples spanning five unique evaluation tasks (pairwise, step-level, reference-free and reference-based verification, and single rating) and multiple domains focused on reasoning evaluation. With our data, we train Foundational Automatic Reasoning Evaluators (FARE), a family of 8B and 20B (with 3.6B active) parameter evaluators, with a simple iterative rejection-sampling supervised finetuning (SFT) approach. FARE-8B challenges larger specialized RL-trained evaluators and FARE-20B sets the new standard for open-source evaluators, surpassing specialized 70B+ evaluators. Beyond static benchmarks, we evaluate FARE in real-world tasks: As inference-time rerankers, FARE-20B achieves near-oracle performance on MATH. As verifiers in RL training, FARE improves the downstream RL-trained model performance by up to 14.1\% vs. string-matching verifiers. When initialized from FARE, a continually-finetuned FARE-Code outperforms gpt-oss-20B by 65% on evaluating test-case quality

Reinforcement Learning · Deep RL

Tao Ren, Jinyang Jiang, Hui Yang, Wan Tian, Minhao Zou, Guanghao Li, Zishi Zhang, Qinghao Wang, Shentao Qin, Yanjun Zhao 等

Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, such as Group Relative Policy Optimization (GRPO), suffer from entropy collapse and limited reasoning gains. We argue that these issues stem from overemphasizing high-probability output sequences while neglecting rare but informative reasoning paths. To address these challenges, we propose Risk-based Policy Optimization (RiskPO), which substitutes classical mean-based objectives with principled risk measures. Specifically, we introduce a Mixed Value-at-Risk objective that integrates weighted attention over multiple regions of the reward distribution, thereby amplifying gradient signals on challenging instances and preventing overconfident convergence. We further design a bundling scheme that aggregates multiple questions into bundles, thus enriching the feedback signal and yielding more stable and informative training dynamics. Theoretically, we prove that the risk-averse update alleviates entropy collapse and promotes exploration. Numerically, RiskPO achieves consistent and significant improvements in mathematical reasoning, multi-modal reasoning, and code generation benchmarks, surpassing GRPO and its variants on both Pass@1 and Pass@k metrics. Our results demonstrate that risk-based optimization provides a rigorous and effective paradigm for enhancing LLM reasoning capabilities. The implementation is available at https://github.com/RTkenny/RiskPO.

Reinforcement Learning · Deep RL

Fang Wu, Weihao Xuan, Heli Qi, Aaron Tu, Ximing Lu, Li Li, Yejin Choi

Although Reinforcement Learning with Verifiable Rewards (RLVR) has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus after thousands of optimization steps, i.e., notable decreases in performance gains despite increased computational investment. This limitation stems from the sparse exploration patterns inherent in current RLVR practices, where models rely on limited rollouts that often miss critical reasoning paths and fail to provide systematic coverage of the solution space. We present DeepSearch, a framework that integrates Monte Carlo Tree Search (MCTS) directly into RLVR training. In contrast to existing methods that rely on tree search only at inference, DeepSearch embeds structured search into the training loop, enabling systematic exploration and fine-grained credit assignment across reasoning steps. Through training-time exploration, DeepSearch addresses the fundamental bottleneck of insufficient exploration, which leads to diminishing performance gains over prolonged training. Our contributions include: (1) a global frontier selection strategy that prioritizes promising nodes across the search tree, (2) selection with entropy-based guidance that identifies confident paths for supervision, and (3) adaptive replay buffer training with solution caching for efficiency. Experiments on mathematical reasoning benchmarks show that DeepSearch achieves an average accuracy of 62.95% and establishes a new state-of-the-art reasoning model, while using 5.7x fewer GPU hours than extended training approaches. These results highlight the importance of strategic exploration over brute-force scaling and demonstrate the promise of algorithmic innovation for advancing RLVR methodologies. DeepSearch establishes a new direction for scaling reasoning capabilities through systematic search rather than prolonged computation.

Deep Learning · Everything Else

Da Ma, Ziyue Yang, Hongshen Xu, Haotian Fang, Kai Yu, Lu Chen

Large Language Models (LLMs) have recently alleviated limitations in outdated internal knowledge and computational inaccuracies by invoking external tools such as search engines and code generation. While reinforcement learning (RL) has substantially enhanced tool usage in LLMs, most existing agentic RL approaches rely solely on outcome-only reward signals, which assign credit at a coarse granularity and often induce gradient conflict (e.g., correct tool calls may be penalized due to incorrect final answers). To address this, we propose the *Tool-call Reward Model* (TRM), a specialized process reward model meticulously designed to evaluate and reward each tool invocation. Since previous PRM research has predominantly focused on traditional reasoning tasks such as step-wise mathematical reasoning, the introduction of TRM brings two unique challenges: (1) limited understanding of how to construct effective TRMs, including data requirements and model size; and (2) difficulties integrating TRM with classical RL algorithms such as PPO and GRPO, where naive adaptation may lead to reward hacking (minimizing tool calls to avoid penalties). To tackle these challenges, we establish a systematic TRM construction workflow and propose refined credit assignment and turn-level advantage estimation for effective integration with PPO and GRPO. Experiments show that a 3B TRM trained on 10K samples achieves robust performance. On search-based QA and Python code-based math tasks, integrating TRM consistently outperforms outcome-only reward RL methods across models of different sizes.

Deep Learning · Everything Else

Wenkai Yang, Weijie Liu, Ruobing Xie, Yiju Guo, Lulu Wu, Saiyong Yang, Yankai Lin

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). To address the lack of verification signals at test time after RLVR, prior studies incorporate the training of model's self-verification capabilities into the standard RLVR process, thereby unifying reasoning and verification capabilities within a single LLM. However, previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which doubles the inference cost per sample and significantly reduces efficiency. In this work, we theoretically reveal that the closed-form solution to the RL objective of self-verification training can be approximately reduced to a remarkably simple form: the true reasoning reward of a solution is equal to its last-token self-rewarding score, which is computed as the difference between the policy model's next-token log-probability assigned to any pre-specified token at the solution's last token and a pre-calculated constant, scaled by the KL coefficient. Based on this insight, we propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a Mean Squared Error (MSE) loss that aligns the last-token self-rewarding scores with the verifier-based reasoning rewards, and jointly optimizes the reasoning and self-rewarding capabilities of LLMs. The optimized self-rewarding scores serve as auxiliary reward signals in both training and testing to enhance model performance. Notably, our algorithm derives these scores from the predicted next-token probability distribution of the last solution token immediately after solution generation, thereby incurring only the minimal extra cost of at most one additional token inference. Experimental results show that our method not only improves the reasoning performance of the model also equips it with remarkable self-rewarding capability, thereby further boosting its inference-time scaling performance.

Reinforcement Learning · Deep RL

Ruike Cao, Shaojie Bai, Fugen Yao, Liang Dong, Jian Xu, Li Xiao

Effective information seeking in multi-turn medical dialogues is critical for accurate diagnosis, especially when dealing with incomplete information. Aligning Large Language Models (LLMs) for these interactive scenarios is challenging due to the uncertainty inherent in user-agent interactions, which we formulate as a Hierarchical Markov Decision Process (H-MDP). While conventional Reinforcement Learning (RL) methods like Group Relative Policy Optimization (GRPO) struggle with long-horizon credit assignment and Proximal Policy Optimization (PPO) suffers from unstable value estimation in this context, we propose a novel uncertainty-aware Adaptive Tree Policy Optimization (ATPO) algorithm. Our method adaptively allocates the rollout budget to states with high uncertainty, quantified by a composite metric of Bellman error and action-value variance. This strategy enables more accurate value estimation, while fostering more efficient and diverse exploration. To mitigate the high computational cost of tree-based RL, we introduce two key optimizations: an uncertainty-guided pruning mechanism to minimize the number of rollouts, and an asynchronous search architecture that leverages KV cache reuse to maximize inference throughput. Extensive experiments on three public medical dialogue benchmarks demonstrate that our algorithm significantly outperforms several strong baselines, culminating in Qwen3-8B model surpassing the much larger GPT-4o (+0.92% accuracy).

Reinforcement Learning · Deep RL

Baptiste Debes, Tinne Tuytelaars

Gradient-regularized value learning methods improve sample efficiency by leveraging learned models of transition dynamics and rewards to estimate return gradients. However, existing approaches, such as MAGE, struggle in stochastic or noisy environments, limiting their applicability. In this work, we address these limitations by extending distributional reinforcement learning on continuous state-action spaces to model not only the distribution over scalar state-action value functions but also over their gradients. We refer to this approach as Distributional Sobolev Training. Inspired by Stochastic Value Gradients (SVG), our method utilizes a one-step world model of reward and transition distributions implemented via a conditional Variational Autoencoder (cVAE). The proposed framework is sample-based and employs Max-sliced Maximum Mean Discrepancy (MSMMD) to instantiate the distributional Bellman operator. We prove that the Sobolev-augmented Bellman operator is a contraction with a unique fixed point, and highlight a fundamental smoothness trade-off underlying contraction in gradient-aware RL. To validate our method, we first showcase its effectiveness on a simple stochastic reinforcement‐learning toy problem, then benchmark its performance on several MuJoCo environments.

Reinforcement Learning · Deep RL

Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li

Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language models (VLMs) to augment rewards of a task with visual feedback. A common practice linearly adds VLM scores to task or success rewards without explicit shaping, potentially altering the optimal policy. Moreover, such approaches, often relying on single static images, struggle with tasks whose desired behavior involves complex, dynamic motions spanning multiple visually different states. Furthermore, single viewpoints can occlude critical aspects of an agent's behavior. To address these issues, this paper presents Multi-View Video Reward Shaping (MVR), a framework that models the relevance of states regarding the target task using videos captured from multiple viewpoints. MVR leverages video-text similarity from a frozen pre-trained VLM to learn a state relevance function that mitigates the bias towards specific static poses inherent in image-based methods. Additionally, we introduce a state-dependent reward shaping formulation that integrates task-specific rewards and VLM-based guidance, automatically reducing the influence of VLM guidance once the desired motion pattern is achieved. We confirm the efficacy of the proposed framework with extensive experiments on challenging humanoid locomotion tasks from HumanoidBench and manipulation tasks from MetaWorld, verifying the design choices through ablation studies.

Deep Learning · Everything Else

Natasha Butt, Ariel Kwiatkowski, Ismail Labiad, Julia Kempe, Yann Ollivier

The use of continuous instead of discrete tokens during the Chain-of-Thought (CoT) phase of reasoning LLMs has garnered attention recently, based on the intuition that a continuous mixture of discrete tokens could simulate a superposition of several reasoning paths simultaneously. Theoretical results have formally proven that continuous tokens have much greater expressivity and can solve specific problems more efficiently. However, practical use of continuous tokens has been limited by strong training difficulties: previous works either just use continuous tokens at inference time on a pre-trained discrete-token model, or must distill the continuous CoT from ground-truth discrete CoTs and face computational costs that limit the CoT to very few tokens. This is the first work introducing a scalable method to learn continuous CoTs via reinforcement learning (RL), without distilling from reference discrete CoTs. We use "soft" tokens: mixtures of tokens together with noise on the input embedding to provide RL exploration. Computational overhead is minimal, enabling us to learn continuous CoTs with hundreds of tokens. On math reasoning benchmarks with Llama and Qwen models up to 8B, training with continuous CoTs match discrete-token CoTs for pass@$1$ and surpass them for pass@$32$, showing greater CoT diversity. In systematic comparisons, the best-performing scenario is to train with continuous CoT tokens then use discrete tokens for inference, meaning the "soft" models can be deployed in a standard way. Finally, we show continuous CoT RL training better preserves the predictions of the base model on out-of-domain tasks, thus providing a softer touch to the base model.

Deep Learning · Generative Models and Autoencoders

Mehul Damani, Isha Puri, Stewart Slocum, Idan Shenfeld, Leshem Choshen, Yoon Kim, Jacob Andreas

When language models (LMs) are trained via reinforcement learning (RL) to generate natural language “reasoning chains”, their performance improves on a variety of difficult question answering tasks. Today, almost all successful applications of RL for reasoning use binary reward functions that evaluate the correctness of LM outputs. Because such reward functions do not penalize guessing or low-confidence outputs, they often have the unintended side-effect of degrading calibration and increasing the rate at which LMs generate incorrect responses (or “hallucinate”) in other problem domains. This paper describes RLCR (Reinforcement Learning with Calibration Rewards), an approach to training reasoning models that jointly improves accuracy and calibrated confidence estimation. During RLCR, LMs generate both predictions and numerical confidence estimates after reasoning. They are trained to optimize a reward function that augments a binary correctness score with a Brier score—a scoring rule for confidence estimates that incentivizes calibrated prediction. We first prove that this reward function (or any analogous reward function that uses a bounded, proper scoring rule) yields models whose predictions are both accurate and well-calibrated. We next show that across diverse datasets, RLCR substantially improves calibration with no loss in accuracy, on both in-domain and out-of-domain evaluations—outperforming both ordinary RL training and classifiers trained to assign post-hoc confidence scores. While ordinary RL hurts calibration, RLCR improves it. Finally, we demonstrate that verbalized confidence can be leveraged at test time to improve accuracy and calibration via confidence-weighted scaling methods. Our results show that explicitly optimizing for calibration can produce more generally reliable reasoning models.

Reinforcement Learning · Deep RL

Yiyou Sun, Yuhan Cao, Pohao Huang, Haoyue Bai, Hanna Hajishirzi, Nouha Dziri, Dawn Song

It remains an open question whether LLMs can acquire or generalize genuinely new reasoning strategies, beyond the sharpened skills encoded in their parameters during pre-training or post-training. To attempt to answer this debate, we introduce DELTA — Distributional Evaluation of Learnability and Transferrability in Algorithmic Coding, a controlled benchmark of synthetic coding problem families designed to probe two fundamental aspects: learnability—can LLMs, through reinforcement learning (RL), solve problem families where pretrained models exhibit failure with large enough attempts (pass@K=0)?—and transferability—if learnability happens, can such skills transfer systematically to out-of-distribution (OOD) test sets? Unlike prior public coding datasets, DELTA isolates reasoning skills through templated problem generators and introduces fully OOD problem families that demand novel strategies rather than tool invocation or memorized patterns. Our experiments reveal a striking grokking phase transition: after an extended period with near-zero reward, RL-trained models abruptly climb to near-perfect accuracy. To enable learnability on previously unsolvable problem families, we explore key training ingredients such as staged warm-up with dense rewards, experience replay, curriculum training, and verification-in-the-loop. Beyond learnability, we use DELTA to evaluate transferability or generalization along exploratory, compositional, and transformative axes, as well as cross-family transfer. Results show solid gains within families and for recomposed skills, but persistent weaknesses in transformative cases. DELTA thus offers a clean testbed for probing the limits of RL-driven reasoning and for understanding how models can move beyond existing priors to acquire new algorithmic skills.

Reinforcement Learning · Deep RL

Haoran Xu, Kaiwen Hu, Somayeh Sojoudi, Amy Zhang

We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by erroneous out-of-distribution extrapolation. Existing methods either rely on reparameterized policy gradient, which are difficult to scale to large generative models, or on reject sampling, which can be overly conservative when attempting to move beyond the behavior support. In this paper, we propose Value Gradient Flow (VGF), a scalable new paradigm for behavior-regularized RL. VGF casts behavior-regularized RL as an optimal transport problem that maps the reference distribution to the value-induced optimal policy distribution. We solve this transport problem via discrete gradient flow, where value gradients guide particles initialized from the reference distribution. Our analysis shows that VGF imposes regularization implicitly by controlling the transport budget. VGF eliminates explicit policy parameterization while remaining expressive and flexible, this enables adaptive test-time scaling by adjusting the transport budget. Extensive experiments demonstrate that VGF significantly outperforms prior methods, achieving state-of-the-art results on offline RL benchmarks (D4RL, OGBench) and LLM RL tasks.

Reinforcement Learning · Deep RL

Faisal Mohamed, Catherine Ji, Benjamin Eysenbach, Glen Berseth

Effective exploration in reinforcement learning requires not only tracking where an agent has been, but also understanding how the agent perceives and represents the world. To learn powerful representations, an agent should actively explore states that contribute to its knowledge of the environment. Temporal representations can capture the information necessary to solve a wide range of potential tasks while avoiding the computational cost associated with full state reconstruction. In this paper, we propose an exploration method that leverages temporal contrastive representations to guide exploration, prioritizing states with unpredictable future outcomes. We demonstrate that such representations can enable the learning of complex exploratory behaviors in locomotion, manipulation, and embodied-AI tasks, revealing capabilities and behaviors that traditionally require extrinsic rewards. Unlike approaches that rely on explicit distance learning or episodic memory mechanisms (e.g., quasimetric-based methods), our method builds directly on temporal similarities, yielding a simpler yet effective strategy for exploration.

Reinforcement Learning · Deep RL

Zihe Liu, Jiashun Liu, Yancheng He, Weixun Wang, JIAHENG LIU, Ling Pan, Xinyu Hu, Shaopan Xiong, Ju Huang, Jian Hu 等

Reinforcement learning (RL) for LLM reasoning has rapidly emerged as a prominent research area, marked by a significant surge in related studies on both algorithmic innovations and practical applications. Despite this progress, several critical challenges remain, including the absence of standardized guidelines for applying RL techniques and a fragmented understanding of their underlying mechanisms. In addition, inconsistent experimental settings, variations in training data, and differences in model initialization have led to conflicting conclusions, obscuring the key characteristics of these techniques and creating confusion among practitioners when selecting appropriate techniques. This paper systematically reviews widely adopted RL techniques through rigorous reproductions and isolated evaluations within a unified open-source framework. We analyze the internal mechanisms, applicable scenarios, and core principles of each technique through fine-grained experiments, including datasets of varying difficulty, model sizes, and architectures. Based on these insights, we present clear guidelines for selecting RL techniques tailored to specific setups and provide a reliable roadmap for practitioners navigating the RL for the LLM domain. Finally, we show that a minimalist combination of two techniques can unlock the learning capability of critic-free policies with a vanilla PPO loss. The results demonstrate that our simple combination consistently improves performance, surpassing strategies such as GRPO and DAPO.