论文检索

Reinforcement Learning · Deep RL

Jens Tuyls, Dylan Foster, Akshay Krishnamurthy, Jordan Ash

Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration---explicitly incentivizing the model to discover novel and diverse behaviors---and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration with a simple, principled, representation-based bonus derived from the pre-trained language model's hidden states significantly improves diversity and pass@k rates---both for post-training, and in a novel inference-time scaling setting we introduce. (1) For inference-time, exploration with representation-based diversity improves efficiency, consistently improving pass@k rates across a variety of models and reasoning tasks. For example, for Qwen-2.5-14b-Instruct we obtain over 50\% improvement in verifier efficiency on almost all considered tasks. (2) For post-training, we show that integrating this exploration strategy into an RL pipeline improves reasoning performance over that of the initial model and over standard RL post-training. For example, on AIME 2024, our post-trained Qwen-2.5-7b-Instruct's pass@80 matches the pass@256 of GRPO on the same model, demonstrating a 3x improvement in test-time sample efficiency. Overall, our findings suggest that deliberate exploration---with the right notion of diversity---is a practical path toward discovery of new behaviors beyond sharpening.

Reinforcement Learning · Deep RL

Geonwoo Cho, Jaemoon Lee, Jaegyun Im, Subi Lee, Jihwan Lee, Sundong Kim

Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires jointly maximizing both exploration and skill diversity. However, existing methods often face challenges in simultaneously optimizing for these two conflicting objectives. In this work, we propose a new method, Adaptive Multi-objective Projection for balancing Exploration and skill Diversification (AMPED), which explicitly addresses both: during pre-training, a gradient-surgery projection balances the exploration and diversity gradients, and during fine-tuning, a skill selector exploits the learned diversity by choosing skills suited to downstream tasks. Our approach achieves performance that surpasses SBRL baselines across various benchmarks. Through an extensive ablation study, we identify the role of each component and demonstrate that each element in AMPED is contributing to performance. We further provide theoretical evidence that, with a greedy skill selector, greater skill diversity reduces fine-tuning sample complexity. These results highlight the importance of explicitly harmonizing exploration and diversity and demonstrate the effectiveness of AMPED in enabling robust and generalizable skill learning. https://geonwoo.me/amped/

Reinforcement Learning · Deep RL

Waris Radji, Thomas Michel, Hector Piteau

Reinforcement learning (RL) research requires diverse, challenging environments that are both tractable and scalable. While modern video games may offer rich dynamics, they are computationally expensive and poorly suited for large-scale experimentation due to their CPU-bound execution. We introduce Octax, a high-performance suite of classic arcade game environments implemented in JAX, based on CHIP-8 emulation, a predecessor to Atari, which is widely adopted as a benchmark in RL research. Octax provides the JAX community with a long-awaited end-to-end GPU alternative to Atari games, offering image-based environments, spanning puzzle, action, and strategy genres, all executable at massive scale on modern GPUs. Our JAX-based implementation achieves orders-of-magnitude speedups over traditional CPU emulators. We demonstrate Octax's capabilities by training RL agents across multiple games, showing significant improvements in training speed and scalability compared to existing solutions. The environment's modular design enables researchers to easily extend the suite with new games or generate novel environments using large language models, making it an ideal platform for large-scale RL experimentation. Our open-source framework is available at https://github.com/riiswa/octax/.

Reinforcement Learning · Deep RL

Yaoyu Wang, Hankun Dai, Zhidong Yang, Junmin Xiao, Guangming Tan

Code generation is a crucial research area in the field of artificial intelligence, holding the potential to revolutionize software development and streamline programming processes. However, generating the high-performance code, which need to be executed in a shorter time for the low-latency scenario, remains a formidable challenge. Existing methods often struggle to account for the irregularity of input sparse data in sparse programs and the need for domain-specific architectural knowledge, leading to sub-optimal performance. To tackle these issues, we propose the SparseRL framework. SparseRL leverages deep reinforcement learning, treating a pre-trained language model as a stochastic policy. It takes the row and column indices of non-zero elements in the sparse matrix as input and generates CUDA code as output for sparse matrix operations. We also introduce a domain-specific code generation mechanism for the dynamic input, a sinusoidal embedding technique tailored for sparse matrices, and a hierarchical reward function that considers both code correctness and execution efficiency. Experimental results demonstrate SparseRL achieves state-of-the-art performance. In sparse matrix-vector multiplication (SpMV) tasks, it improves the compilation rate by 20% compared to existing methods, and the generated code runs 30% faster on average. For sparse matrix-dense matrix multiplication (SpMM) tasks, SparseRL also shows significant performance gains. These results highlight the effectiveness of SparseRL in generating high-performance CUDA code for sparse matrix operations.

Reinforcement Learning · Deep RL

Jing Liang, Jinyi Liu, Yi Ma, Hongyao Tang, YAN ZHENG, Shuyue Hu, LEI BAI, Jianye Hao

Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs), yet most existing Reinforcement Finetuning (RFT) methods are inherently *on-policy* RL, failing to reuse historical data and thus preventing efficient scaling. In this work, we explore the potential of *off-policy* RL to leverage historical data for rollout-efficient RFT. Specifically, we propose **Re**incarnating **Mix**-policy Proximal Policy Gradient (**ReMix**), which enables on-policy RFT methods to leverage off-policy data. ReMix consists of three major components: (1) Mix-policy proximal policy gradient with an increased Update-To-Data (UTD) ratio that utilizes the data from both current and past policies for efficient training; (2) KL-Convex policy constraint that combines the KL constraints on the base and precedent model to balance stability and flexibility; (3) Policy reincarnation that replaces the base model with the mix-policy RFT model in the mid way of training and restarts on-policy training, to achieve a seamless transition from early efficiency to steady convergence. In our experiments, we train a series of ReMix models based on PPO, GRPO from 1.5B, 7B base models. On five math reasoning benchmarks (i.e., AIME'24, AMC'23, Minerva, OlympiadBench, and MATH500), ReMix achieves an average Pass@1 accuracy of **52.10%** (with **0.079M rollouts**) and **64.39%** (with **0.011M rollouts**) on 1.5B and 7B models, respectively. Compared with 15 recent advanced models, ReMix shows SOTA-level performance with an over **30x to 450x reduction in training cost in terms of rollout data volume**, demonstrating superior training efficiency. Additionally, our multifaceted analysis reveals insightful findings, including the implicit preference for shorter responses of off-policy RFT, the collapse mode of self-reflection under severe off-policyness, etc. The code and the trained models are available at https://anitaleungxx.github.io/ReMix/ .

Reinforcement Learning · Deep RL

Shenao Zhang, Yaqing Wang, Yinxiao Liu, Tianqi Liu, Peter Grabowski, Eugene Ie, Zhaoran Wang, Yunxuan Li

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error correction, as a form of in-context exploration. However, the Markovian policy obtained from conventional RL training does not give rise to reflective exploration behaviors since the policy depends on the history only through the state and therefore has no incentive to enrich identical states with additional context. Instead, RL exploration is only useful during training to learn the optimal policy in a trial-and-error manner. Therefore, it remains unclear whether reflective reasoning will emerge during RL, or why it is beneficial. To remedy this, we recast reflective exploration within a Bayesian RL framework, which optimizes the expected return under a posterior distribution over Markov decision processes induced by the training data. This Bayesian formulation admits uncertainty-adaptive policies that, through belief updates, naturally incentivize information-gathering actions and induce self-reflection behaviors. Our resulting algorithm, BARL, instructs the LLM to stitch and switch strategies based on the observed outcomes, offering principled guidance on when and how the model should reflectively explore. Empirical results on both synthetic and mathematical reasoning tasks demonstrate that BARL outperforms conventional RL approaches, achieving superior test-time performance and token efficiency. Our code is available at https://github.com/shenao-zhang/BARL.

Reinforcement Learning · Deep RL

Seungyul Han, Jaebak Hwang, Sanghyeon Lee, Jeongmo Kim

Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While hierarchical and graph-based methods offer partial solutions, their reliance on conventional hindsight relabeling often fails to correct subgoal infeasibility, leading to inefficient high-level planning. To address this, we propose Strict Subgoal Execution (SSE), a graph-based hierarchical RL framework that integrates Frontier Experience Replay (FER) to separate unreachable from admissible subgoals and streamline high-level decision making. FER delineates the reachability frontier using failure and partial-success transitions, which identifies unreliable subgoals, increases subgoal reliability, and reduces unnecessary high-level decisions. Additionally, SSE employs a decoupled exploration policy to cover underexplored regions of the goal space and a path refinement that adjusts edge costs using observed low-level failures. Experimental results across diverse long-horizon benchmarks show that SSE consistently outperforms existing goal-conditioned and hierarchical RL methods in both efficiency and success rate.

Reinforcement Learning · Deep RL

Haoran He, Yuxiao Ye, Qingpeng Cai, Chen Hu, Binxing Jiao, Daxin Jiang, Ling Pan

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow generalized policy iteration that alternates between evaluating the current policy's value and improving the policy based on evaluation. While effective, they often suffer from training instability and diversity collapse, requiring complex heuristic tricks and careful tuning. We observe that standard RLVR in math reasoning can be formalized as a specialized finite-horizon Markov Decision Process with deterministic state transitions, tree-structured dynamics, and binary terminal rewards. Though large in scale, the underlying structure is simpler than general-purpose control settings for which popular RL algorithms (e.g., PPO) were developed, suggesting that several sophisticated techniques in existing methods may be reduced or even omitted. Based on this insight, we prove a surprising result: the optimal action can be recovered from the Q-function of a fixed uniformly random policy, thereby bypassing the generalized policy iteration loop and its associated heuristics. We introduce \underline{\textbf{R}}andom P\underline{\textbf{o}}licy \underline{\textbf{V}}aluation for Div\underline{\textbf{e}}rse \underline{\textbf{R}}easoning (ROVER) to translate this principle into a practical and scalable algorithm for LLM math reasoning, a minimalist yet highly effective RL method that samples actions from a softmax over these uniform-policy Q-values. ROVER preserves diversity throughout training, allowing sustained exploration of multiple valid pathways. Across multiple base models and standard math reasoning benchmarks, ROVER demonstrates superior performance in both \textbf{quality} (\textbf{+8.2} on pass@1, \textbf{+16.8} on pass@256) and \textbf{diversity} (\textbf{+20.5\%}), despite its radical simplification compared to strong, complicated existing methods.

Reinforcement Learning · Deep RL

Yule Zhong, Jiacheng Yao, Guoxiu He

While supervised fine-tuning (SFT) and preference learning (PL) are widely used to enhance the instruction-following ability of Large Language Models (LLMs), they often struggle to generalize to novel or complex instructions and may compromise the models' general capabilities. In-Context Learning (ICL) emerges as a promising alternative due to its strong generalization without modifying the model's parameters, but its effectiveness is constrained by the reliance on high-quality, manually curated demonstration pools. To overcome this limitation, we propose ContextIF, a reinforcement learning (RL) framework for automatic context generation. Guided by comprehensive context reward, ContextIF is optimized by Group Relative Policy Optimization (GRPO). It aims to generate precise constraint summaries and optimal context demonstrations tailored to given instructions, thereby improving the instruction-following performance of target LLMs. We evaluate ContextIF on multiple representative instruction-following benchmarks using popular open-source LLMs. Experimental results demonstrate that ContextIF achieves substantial performance gains over existing SFT and ICL methods, while also generalizing effectively to unseen constraint conditions. Moreover, ContextIF preserves the parameters and general capabilities of the target models, offering strong adaptability and scalability. Our code is available at https://github.com/ECNU-Text-Computing/ContextIF.

Reinforcement Learning · Deep RL

Seungyul Han, Sanghyeon Lee, Sangjun Bae, Yisak Park

Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decomposing state-action sequences into reusable skills and employing hierarchical decision-making. However, these methods are highly susceptible to noisy offline demonstrations, leading to unstable skill learning and degraded performance. To address this, we propose Self-Improving Skill Learning (SISL), which performs self-guided skill refinement using decoupled high-level and skill improvement policies, while applying skill prioritization via maximum return relabeling to focus updates on task-relevant trajectories, resulting in robust and stable adaptation even under noisy and suboptimal data. By mitigating the effect of noise, SISL achieves reliable skill learning and consistently outperforms other skill-based meta-RL methods on diverse long-horizon tasks. Our code is available at https://github.com/epsilog/SISL.

Deep Learning · Algorithms

Aayush Karan, Yilun Du

Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilities can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models' own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains.

Reinforcement Learning · Deep RL

Leonard S. Pleiss, Tobias Sutter, Maximilian Schiffer

Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific learning potential. In an effort to sample more efficiently, researchers introduced Prioritized Experience Replay (PER). In this paper, we propose an extension to PER by introducing a novel measure of temporal difference error reliability. We theoretically show that the resulting transition selection algorithm, Reliability-adjusted Prioritized Experience Replay (ReaPER), enables more efficient learning than PER. We further present empirical results showing that ReaPER outperforms both uniform experience replay and PER across a diverse set of traditional environments including several classic control environments and the Atari-10 benchmark, which approximates the median score across the Atari-57 benchmark within one percent of variance.

Reinforcement Learning · Deep RL

Vittorio Giammarino, Ahmed Hussain Qureshi

Goal-Conditioned Reinforcement Learning (GCRL) mitigates the difficulty of reward design by framing tasks as goal reaching rather than maximizing hand-crafted reward signals. In this setting, the optimal goal-conditioned value function naturally forms a quasimetric, motivating Quasimetric RL (QRL), which constrains value learning to quasimetric mappings and enforces local consistency through discrete, trajectory-based constraints. We propose Eikonal-Constrained Quasimetric RL (Eik-QRL), a continuous-time reformulation of QRL based on the Eikonal Partial Differential Equation (PDE). This PDE-based structure makes Eik-QRL trajectory-free, requiring only sampled states and goals, while improving out-of-distribution generalization. We provide theoretical guarantees for Eik-QRL and identify limitations that arise under complex dynamics. To address these challenges, we introduce Eik-Hierarchical QRL (Eik-HiQRL), which integrates Eik-QRL into a hierarchical decomposition. Empirically, Eik-HiQRL achieves state-of-the-art performance in offline goal-conditioned navigation and yields consistent gains over QRL in manipulation tasks, matching temporal-difference methods.

Reinforcement Learning · Deep RL

Pranaya Jajoo, Harshit Sikchi, Siddhant Agarwal, Amy Zhang, Scott Niekum, Martha White

Behavioral Foundation Models (BFMs) have been recently successful in producing agents with the capabilities to adapt to any unknown reward or task. In reality, these methods are only able to produce near-optimal policies for the reward functions that are in the span of some pre-existing _state features_. Naturally, their efficiency relies heavily on the choice of state features that they use. As a result, these BFMs have used a wide variety of complex objectives, often sensitive to environment coverage, to train task spanning features with different inductive properties. With this work, our aim is to examine the question: are these complex representation learning objectives necessary for zero-shot RL? Specifically, we revisit the objective of self-supervised next-state prediction in latent space for state feature learning, but observe that such an objective alone is prone to increasing state-feature similarity, and subsequently reducing span of reward functions that we can represent optimal policies for. We propose an approach, RLDP, that adds a simple regularization to maintain feature diversity and can match or surpass state-of-the-art complex representation learning methods for zero-shot RL. Furthermore, we demonstrate the prior approaches diverge in low-coverage scenarios where RLDP still succeeds.

Reinforcement Learning · Deep RL

Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli

Despite its recent successes, Deep Reinforcement Learning (DRL) is notoriously sample-inefficient. We argue that this inefficiency stems from the standard practice of optimizing policies directly in the high-dimensional and highly redundant parameter space $\\Theta$. This challenge is greatly compounded in multi-task settings. In this work, we develop a novel, unsupervised approach that compresses the policy parameter space $\\Theta$ into a low-dimensional latent space $\\mathcal Z$. We train a generative model $g:\\mathcal Z\\to\\Theta$ by optimizing a behavioral reconstruction loss, which ensures that the latent space is organized by functional similarity rather than proximity in parameterization. We conjecture that the inherent dimensionality of this manifold is a function of the environment's complexity, rather than the size of the policy network. We validate our approach in continuous control domains, showing that the parameterization of standard policy networks can be compressed up to five orders of magnitude while retaining most of its expressivity. As a byproduct, we show that the learned manifold enables task-specific adaptation via Policy Gradient operating in the latent space $\\mathcal{Z}$.

Reinforcement Learning · Deep RL

Ke Sun, Hongming Zhang, Jun Jin, Chao Gao, Xi Chen, Wulong Liu, Linglong Kong

Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a fast learner and a meta learner to address continual Reinforcement Learning~(RL) problems. These two learners are coupled to perform distinct yet complementary roles: the fast learner focuses on knowledge transfer, while the meta learner ensures knowledge integration. In contrast to traditional multi-task RL approaches that share knowledge through average return maximization, our meta learner incrementally integrates new experiences by explicitly minimizing catastrophic forgetting, thereby supporting efficient cumulative knowledge transfer for the fast learner. To facilitate rapid adaptation in new environments, we introduce an adaptive meta warm-up mechanism that selectively harnesses past knowledge. We conduct experiments in various pixel-based and continuous control benchmarks, revealing the superior performance of continual learning for our proposed dual-learner approach relative to baseline methods.

Reinforcement Learning · Deep RL

Guoqing Wang, Sunhao Dai, Guangze Ye, Zeyu Gan, Wei Yao, Yong Deng, Xiaofeng Wu, zhenzhe ying

Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require multi-turn reasoning and knowledge acquisition. However, existing approaches typically rely on outcome-based rewards that are only provided exclusively upon generating the final answer. This reward sparsity becomes particularly problematic in multi-turn settings, where long trajectories exacerbate three critical issues: (i) advantage collapse, where all rollouts receive identical rewards and provide no useful learning signals; (ii) lack of fine-grained credit assignment, where the correctness of intermediate turns is obscured, especially in long-horizon tasks; and (iii) poor sample efficiency, where each rollout yields only a single outcome signal, leading to low data utilization. In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training. IGPO models each interaction turn as an incremental process of acquiring information about the ground truth, and defines turn-level rewards as the marginal increase in the policy's probability of producing the correct answer. Unlike prior process-level reward approaches that depend on external reward models or costly Monte Carlo estimation, IGPO derives intrinsic rewards directly from the model's own belief updates. These intrinsic turn-level rewards are combined with outcome-level supervision to form dense reward signals. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that IGPO consistently outperforms strong baselines in multi-turn scenarios, achieving higher accuracy and improved data efficiency. Our code is available at https://github.com/GuoqingWang1/IGPO.

Reinforcement Learning · Deep RL

Théo Vincent, Daniel Palenicek, Boris Belousov, Jan Peters, Carlo D Eramo, Théo Vincent

The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall performance and the sample-efficiency of the learning procedure. Typically, action-value functions are estimated through an iterative scheme that alternates the application of an empirical approximation of the Bellman operator and a subsequent projection step onto a considered function space. It has been observed that this scheme can be potentially generalized to carry out multiple iterations of the Bellman operator at once, benefiting the underlying learning algorithm. However, until now, it has been challenging to effectively implement this idea, especially in high-dimensional problems. In this paper, we introduce iterated $Q$-Network (i-QN), a novel principled approach that enables multiple consecutive Bellman updates by learning a tailored sequence of action-value functions where each serves as the target for the next. We show that i-QN is theoretically grounded and that it can be seamlessly used in value-based and actor-critic methods. We empirically demonstrate the advantages of i-QN in Atari $2600$ games and MuJoCo continuous control problems.

Deep Learning · Algorithms

Germàn Kruszewski, Pierre ERBACHER, Jos Rozen, Marc Dymetman

Reinforcement Learning (RL) has become the _de facto_ standard for tuning LLMs to solve tasks involving reasoning. However, growing evidence shows that models trained in such way often suffer from a significant loss in diversity. We argue that this arises because RL implicitly optimizes the "mode-seeking" or "zero-forcing" _Reverse KL_ to a target distribution causing the model to concentrate mass on certain high-probability regions of the target while neglecting others. In this work, we instead begin from an explicit target distribution, obtained by filtering out incorrect answers while preserving the relative probabilities of correct ones. Starting from a pre-trained LLM, we approximate this target distribution using the $\alpha$-divergence family, which unifies prior approaches and enables direct control of the precision–diversity trade-off by interpolating between mode-seeking and mass-covering divergences. On a Lean theorem-proving benchmark, our method achieves state-of-the-art performance along the coverage–precision Pareto frontier, outperforming all prior methods on the coverage axis.

Reinforcement Learning · Deep RL

Thanh-Long V. Le, Myeongho Jeon, Kim Vu, Viet Lai, Eunho Yang

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful framework for improving the reasoning abilities of Large Language Models (LLMs). However, current methods such as GRPO rely only on problems where the model responses to the same input differ in correctness, while ignoring those where all responses receive the same reward — so-called zero-variance prompts. In this work, we argue that such prompts are not useless but can, in fact, provide meaningful feedback for policy optimization. To this end, we introduce Reinforcement Learning with Zero-Variance Prompts (RL-ZVP), a novel algorithm that extract learning signals from zero-variance prompts. RL-ZVP directly rewards correctness and penalizes errors even without contrasting responses, modulating feedback with token-level characteristics to preserve informative, nuanced signals. Across six math reasoning benchmarks, RL-ZVP achieves significant improvements of up to 8.61 points in accuracy and 7.77 points in pass rate over GRPO, while consistently outperforming other baselines that filter out zero-variance prompts. These results highlight the untapped potential of learning from zero-variance prompts in RLVR.