论文检索

General Machine Learning · Causality

Ramon Viñas Torné, Sílvia Fàbregas Salazar, Soyon Park, Ivo Alexander Ban, Artyom Gadetsky, Nikita Doikov, Maria Brbic

Inferring the structure of directed acyclic graphs (DAGs) from data is a central challenge in causal discovery, particularly in modern high-dimensional settings where large-scale interventional data are increasingly available. While interventional data can substantially improve identifiability, existing differentiable causal discovery methods rely on soft acyclicity constraints, leading to optimization over invalid cyclic graphs, numerical instability, and limited scalability. We introduce PACER (Perturbation-driven Acyclic Causal Edge Recovery), a scalable framework for causal discovery that guarantees acyclicity by construction. PACER parameterizes a distribution over DAGs through a joint model of variable permutations and edge probabilities, enabling direct optimization over valid causal structures without surrogate penalties. The framework supports a unified likelihood-based treatment of observational and interventional data, flexible conditional density models, and the incorporation of structural prior knowledge. For linear-Gaussian mechanisms, we derive closed-form expressions for the expected interventional log-likelihood and its gradients, yielding substantial computational gains. Empirically, PACER matches or exceeds state-of-the-art methods on protein signaling and large-scale genetic perturbation benchmarks, while scaling efficiently to networks with thousands of variables and achieving up to two orders of magnitude speedups over penalty-based differentiable approaches. These results demonstrate that exact and scalable causal discovery from high-dimensional perturbation data is achievable through principled search space design.

Deep Learning · Large Language Models

Guinan Su, Yanwu Yang, Li Shen, Lu Yin, Shiwei Liu, Jonas Geiping

Mixture-of-Experts (MoE) models achieve efficient scaling through sparse expert activation, but often suffer from suboptimal routing decisions due to distribution shifts in deployment. While existing test-time adaptation methods could potentially address these issues, they primarily focus on dense models and require access to external data, limiting their practical applicability to MoE architectures. However, we find that, instead of relying on reference data, we can optimize MoE expert selection on-the-fly based only on input context. As such, we propose \textit{a data-free, online test-time framework} that continuously adapts MoE routing decisions during text generation without external supervision or data. Our method cycles between two phases: During the prefill stage, and later in regular intervals, we optimize the routing decisions of the model using self-supervision based on the already generated sequence. Then, we generate text as normal, maintaining the modified router until the next adaption. We implement this through lightweight additive vectors that only update router logits in selected layers, maintaining computational efficiency while preventing over-adaptation. The experimental results show consistent performance gains on challenging reasoning tasks while maintaining robustness to context shifts. For example, our method achieves a 5.5\% improvement on HumanEval with OLMoE. Furthermore, owing to its plug-and-play property, our method naturally complements existing test-time scaling techniques, e.g., achieving 6\% average gains when incorporated with self-consistency on DeepSeek-V2-Lite.

General Machine Learning · Supervised Learning

Guanliang Liu, Wenchao Chen, Long Tian, Xuefei Cao, Hongwei Liu, Bo Chen

Long-tailed recognition suffers from extreme class imbalance, where scarce tail data leads to biased and fragile feature distributions that exacerbate confusion with semantically or visually similar classes. Prior feature-space reconstruction methods transfer head-class structure or train conditional generators to synthesize tail features, yet the resulting statistical updates are often heuristic and can degrade multi-class separability when tail estimates are unreliable. Given this issue, we propose Risk-Bounded Distribution Reconstruction (RBDR), an offline statistic calibration framework for the two-stage long-tailed pipeline, grounded in an analysis of rival-induced discriminative directions. RBDR performs (i) risk-aware mean calibration by softly projecting any candidate update onto a supportive set such that a surrogate discriminative-risk upper bound does not increase, and (ii) covariance control by shrinking dispersion in a rival subspace while preserving diversity in orthogonal components. These plug-and-play modules transform heuristic reconstruction signals into controllable updates, improving performance and stability across multiple long-tailed benchmarks.

General Machine Learning · Evaluation

Jiayi Nie, Haoran Wu, Yao Lai, Zeyu Cao, Cheng Zhang, Binglei Lou, Erwei Wang, Jianyi Cheng, Timothy Jones, Robert Mullins 等

New AI accelerators with novel instruction set architectures (ISAs) often require developers to manually craft low-level kernels - a time-consuming, laborious, and error-prone process that cannot scale across diverse hardware targets. This prevents emerging hardware platforms from reaching the market efficiently. While prior LLM-based code generation has shown promise in mature GPU ecosystems, it remains unclear whether agentic LLM systems can quickly produce valid and efficient kernels for emerging hardware with new ISAs. We present KernelCraft: the first benchmark to evaluate an LLM agent’s ability to generate and optimize low-level kernels for customized accelerators via a function-calling, feedback-driven workflow. Within KernelCraft, the agent refines kernels under ISA and hardware constraints using automated feedback derived from compilation checks, simulation, and correctness validation against ground truth. In our experiments, we assess agent performance across three emerging accelerator platforms on more than 20 ML tasks, each with 5 diverse task configurations, with special evaluation of task configuration complexity. Across four leading reasoning models, top agents produce functionally valid kernels for previously unseen ISAs within a few refinement steps, with optimized kernels that match or outperform template-based compiler baselines. With that, we demonstrate the potential for reducing the cost of kernel development for accelerator designers and kernel developers.

General Machine Learning · Data

Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Aleksandr Golubev

Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution environments and reliable test suites. Although a growing number of benchmarks have emerged, datasets suitable for training remain limited in scale and diversity or often target a limited set of high-resource language ecosystems. We introduce SWE-rebench V2, a language-agnostic automated pipeline for harvesting executable real-world SWE tasks and constructing RL training environments at scale. The pipeline synthesizes repository-specific installation and test procedures via an interactive setup agent, and filters unsound instances using an ensemble of LLM judges, validated against human-verified SWE-bench annotations. Using this pipeline, we construct a dataset of 36,000+ tasks spanning 20 languages and 3,800+ repositories, with pre-built images for reproducible execution. To further scale training data, we additionally release 100,000+ tasks with installation instructions, fail-to-pass tests and rich metadata, where the problem statement is generated based on the original pull request description. We validate the collected instances through a diagnostic study that covers a subset of tasks in five programming languages across seven popular models, and provide instance-level metadata that flags common confounders such as overly restrictive tests and underspecified descriptions. We release the datasets, the collection and execution code, and associated artifacts to enable large-scale training of SWE agents across diverse languages and repositories.

Theory · Deep Learning

Yu Huang, Zixin Wen, Yuejie Chi, Yuting Wei, Aarti Singh, Yingbin LIANG, Yuxin Chen

Reinforcement Learning with Verifiable Rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier to extended reasoning. To understand this, we develop a theory of the training dynamics of RL for transformers on compositional reasoning tasks. Our theory characterizes how the effectiveness of RLVR is governed by the smoothness of the difficulty spectrum. When data contains abrupt discontinuities in difficulty, learning undergoes grokking-type phase transitions, giving rise to prolonged plateaus before progress recurs. In contrast, a smooth difficulty spectrum leads to a *relay effect*: stable gradient signals on easier problems elevate the model's capabilities to the point where harder ones become tractable, resulting in steady and continuous learning. Our theory explains how RLVR can improve performance at the edge of competence, and suggests that appropriately designed data mixtures can yield scalable gains. As a technical contribution, our analysis develops and adapts tools from Fourier analysis on finite groups to our setting. We validate the predicted mechanisms empirically via synthetic experiments.

Deep Learning · Large Language Models

Yifan Wang, Mingxuan Jiang, Zhihao Sun, Yixin Cao, Yicun Liu, Keyang Chen, Guangnan Ye, Hongfeng Chai

Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction. Related queries therefore repeat similar multi-hop traversal, increasing latency and compute. Motivated by \emph{schema}-based learning in cognitive neuroscience, we propose GAM-RAG, a training-free framework that accumulates retrieval experience from recurring or related queries and updates retrieval memory over time. GAM-RAG builds a lightweight, relation-free hierarchical index whose links capture potential co-occurrence rather than fixed semantic relations. During inference, successful retrieval episodes provide sentence-level feedback, updating sentence memories so evidence useful for similar reasoning types becomes easier to activate later. To balance stability and adaptability under noisy feedback, we introduce an uncertainty-aware, \emph{Kalman}-inspired gain rule that jointly updates memory states and perplexity-based uncertainty estimates. It applies fast updates for reliable novel signals and conservative refinement for stable or noisy memories. We provide a theoretical analysis of the update dynamics, and empirically show that GAM-RAG improves average performance by 3.95\% over the strongest baseline and by 8.19\% with 5-turn memory, while reducing inference cost by 61\%.\footnote{Our code and datasets are available at: \url{https://anonymous.4open.science/r/GAM_RAG-2EF6}.}

Liangbin Xie, Zheyuan Li, Fanghua Yu, Xinqi Lin, Jun-hao Zhuang, Jinfan Hu, Jinjin Gu, Jiantao Zhou, Chao Dong

Real-world super-resolution (SR) is challenging due to complex degradations. HYPIR, a recent state-of-the-art diffusion-based restoration model, struggles to deal with this task in a single step. Although a naive two-step cascade improves the results, over-saturation, limited fine-grained details, and high inference latency remain. To address these limitations, we present HYPIR++. It removes the degradation removal encoder and noise augmentation to better preserve fidelity cues from low-quality inputs. To enhance fine-grained detail restoration and local structure fidelity, HYPIR++ introduces a tailored latent ConvNeXt and a latent patch discriminator, enabling adversarial learning directly in the latent space. In addition, HYPIR++ improves inference efficiency by reducing the text sequence length and replacing full attention with sparse neighbor attention, allowing direct processing of high-resolution images without block-based tiling. Extensive experiments demonstrate that HYPIR++ achieves superior perceptual quality and a 1.71× speedup over HYPIR, establishing a new state-of-the-art for real-world SR.

Social Aspects · Accountability, Transparency, and Interpretability

Haoliang Han, Ziyuan Luo, Renjie Wan

3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of 3DGS models across digital platforms create pressing challenges for intellectual property protection and forensic traceability. To address this, we propose GaussTrace, a novel framework for constructing directed provenance graphs for 3DGS models. GaussTrace formulates provenance analysis as an evidence-based reasoning problem. It builds upon attribute-wise statistical profiling of 3DGS parameters to capture intrinsic properties. Moreover, we introduce hypothesis-driven editing simulations of common operations to provide auxiliary evidence for plausible transformation pathways. These statistical and simulated cues jointly enable a Large Language Model (LLM) to perform structured Chain-of-Thought (CoT) reasoning, yielding directional provenance inferences and explainable edge reasons. Experimental results demonstrate that GaussTrace effectively constructs evolutionary relationships among diverse 3DGS models, delivering accurate, interpretable, and robust provenance graphs without requiring model training or access to editing histories.

Deep Learning · Large Language Models

Guozhi Liu, Weiwei Lin, Tiansheng Huang, Ruichao Mo, Qi Mu, Xiumin Wang, Li Shen

Harmful fine-tuning can invalidate safety alignment of large language models, exposing significant safety risks. In this paper, we utilize the attention sink mechanism to mitigate harmful fine-tuning. Specifically, we first measure a statistic named *sink divergence* for each attention head and observe that *different attention heads exhibit two different signs of sink divergence*. To understand its safety implications, we conduct experiments and find that the number of attention heads of positive sink divergence increases along with the increase of the model's harmfulness when undergoing harmful fine-tuning. Based on this finding, we propose a separable sink divergence hypothesis -- *attention heads associating with learning harmful patterns during fine-tuning are separable by their sign of sink divergence*. Based on the hypothesis, we propose a fine-tuning-stage defense, dubbed Surgery. Surgery utilizes a regularizer for sink divergence suppression, which steers attention heads toward the negative sink divergence group, thereby reducing the model’s tendency to learn and amplify harmful patterns. Extensive experiments demonstrate that Surgery improves defense performance by 5.90\%, 11.25\%, and 9.55\% on the BeaverTails, HarmBench, and SorryBench benchmarks, respectively. Source code is available on https://anonymous.4open.science/r/Surgery-A69E.

Applications · Neuroscience, Cognitive Science

Haowei Xu, Yixin Chen, Wanyi Fu, Hongbin Han, Zhaoheng Xie

Neuromodulation can be viewed as closed-loop control of high-dimensional spatiotemporal fields on irregular 3D morphologies, coupling membrane electrophysiology with ionic reaction–diffusion. This view supports high-rate feedback and systematic in-silico evaluation, yet is difficult in practice. Unlike classical PDE control with known equations on regular domains, neuronal microenvironments exhibit complex, often unknown biophysics on irregular shapes. High-fidelity simulators are too costly for real-time control with repeated planning. The discretized field is sparsely observed and must satisfy hard full-field safety constraints. We introduce **NeuronCtrl**, a modular operator-level framework for safe, closed-loop generative control of neuronal microenvironment dynamics. Given measurements, actions, and morphology, a history-conditioned observer infers the latent field, a morphology-aware neural operator predicts one-step dynamics, and a flow-matching conditional flow proposes actions conditioned on user preferences. Safety is enforced via complementary barrier-based mechanisms at both the action and field levels, ensuring constraint satisfaction with minimal intervention. When latency is critical, the multi-step generator is distilled into a single-step policy while retaining the same safety filter. Experiments across three high-fidelity 3D neuromodulation benchmarks spanning deep brain stimulation, extracellular reaction--diffusion control, and astrocytic potassium regulation, demonstrate superior trade-offs among cost, safety, and latency. Code is available at https://anonymous.4open.science/r/NeuronControl-D900.

Deep Learning · Large Language Models

Wenxuan Zhang, Lemeng Wu, Changsheng Zhao, Ernie Chang, Mingchen Zhuge, Zechun Liu, DiJia Su, Hanxian Huang, Jun Chen, Chong Zhou 等

Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation and thus induce new challenges in aligning dLLMs for human preference. In this work, aim to optimize the dLLM generation process by developing a theoretical formulation and an efficient and effective quantification of the probability of generation trajectory. We prove that (i) under reference policy regularization, the probability ratio of intermediate diffusion states equals to that of the newly unmasked tokens, and (ii) the probability of the entire generation can be estimated using a single forward pass with block attention. Integrating the two estimations into preference optimization objective, we propose Trajectory Reduction Policy Optimization (dTRPO). We evaluate dTRPO on 7B dLLMs across instruction-following and reasoning benchmarks and show that it substantially improves the core performance of state-of-the-art dLLMs, achieving gains of up to 9.6\% on STEM tasks, up to 4.3\% on coding tasks, and up to 3.0\% on instruction-following tasks.

Reinforcement Learning · Batch/Offline

Hongqiang Lin, Pengfei Wang, Nenggan Zheng

Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertainty, which arises from limited data coverage (sample-level) and the ambiguity in identifying transition dynamics from finite data (model-level). To provide a unified quantification of these uncertainties, Bayesian RL has been proposed by treating the dynamics model as a random variable and maintaining a corresponding belief. Despite its theoretical appeal, policy optimization in Bayesian RL remains computationally challenging as it requires solving composite objectives with expectations. Prior methods either employ search-based techniques with poor computational scalability or impose restrictive posterior assumptions that sacrifice the adaptability of Bayesian RL. To address these limitations, we propose Posterior Hybrid Bayesian Belief (PhyB), which reformulates the expectation as a convex combination over a subset of dynamics models. Theoretical analysis demonstrates that the objective discrepancy induced by this approximation remains bounded. Based on PhyB, we develop an iterative regularized policy optimization algorithm that provides metric-agnostic guarantees for monotonic improvement until convergence. Empirical results demonstrate that PhyB achieves state-of-the-art performance on various benchmarks.

General Machine Learning · Kernel methods

Rikhav Shah, Sandeep Silwal, Haike Xu

This paper studies the use of *kernel density estimation* (KDE) for linear algebraic tasks involving the *kernel matrix* of a collection of $n$ data points in $\mathbb{R}^d$. In particular, we improve upon the best existing algorithms for computing the following up to $(1+\varepsilon)$ relative error for a Gaussian kernel matrix and other kernels: matrix-vector products, matrix-matrix products, the spectral norm, and sum of all entries. The runtimes of our algorithms depend linearly on the dimension $d$, sub-quadratically in the number of points $n$, and polynomially on the target error $\varepsilon$. Importantly, the dependence on $n$ in each case is far lower when accessing the kernel matrix through KDE queries as opposed to reading individual entries. Our improvements over existing best algorithms (particularly those of [Backurs et al. ICML `21]) for these tasks reduce the polynomial dependence on $\varepsilon$, and additionally decrease the dependence on $n$ in the case of computing the sum of all entries of the kernel matrix. For example, we reduce the power of $1/\epsilon$ from $\approx 7.7$ to $\approx 3.2$ for a $1-\varepsilon$ relative error estimation of the spectral norm of a Gaussian kernel matrix. We complement our upper bounds with several lower bounds for related problems, which provide (conditional) quadratic time hardness results and additionally hint at the limits of KDE based approaches for the problems we study.

Applications · Neuroscience, Cognitive Science

Jingjing Hu, Dan Guo, Haofan Cheng, Zeng ying, Zhan Si, Jinxing Zhou, Meng Wang

Despite the high accuracy of EEG-based emotion recognition, existing models remain opaque "black boxes", lacking semantic grounding between abstract neural features and human-interpretable states. In this paper, we reframe EEG explainability as a cross-modal generation task, shifting the paradigm from feature attribution to behavioral visualization. We introduce Facial Emoji Proxy Modeling, a novel framework that translates high-dimensional EEG signals into identity-agnostic facial emojis. Guided by the neuroscientific prior of neural-facial consistency, this approach grounds neural representations in the manifold of observable facial dynamics. Technically, our framework integrates FMENet, a specialized backbone modeling expression-relevant spatial synergies, and the Facial Emoji Learning Branch (FELB), which treats emoji reconstruction as a structured semantic regularizer. Extensive experiments on EAV and MMER benchmarks demonstrate that our method achieves state-of-the-art accuracy among EEG-only models. Crucially, it generates semantically faithful facial animations that provide a transparent, privacy-preserving window into the brain's emotional evolution, effectively allowing users to "see the emotion" directly from neural signals.

Deep Learning · Large Language Models

Yepeng Liu, Yu Huang, Yu-Xiang Wang, Yingbin LIANG, Yuheng Bu

Convexity recognition plays a central role in many optimization, control, and learning problems. However, the ability of Large Language Models (LLMs) to identify this property in symbolic expressions remains unexamined. We introduce \cb, a scalable and mechanically verifiable benchmark for testing whether LLMs can determine the convexity of a symbolic objective under deep functional composition. Experiments on frontier LLMs reveal a sharp \textit{compositional reasoning gap}: performance degrades rapidly with increasing depth, dropping from an F1-score of $1.0$ at depth $2$ to approximately $0.2$ at depth $100$. Inspection of models' reasoning traces indicates two failure modes: \textit{parsing failure} and \textit{lazy reasoning}. To address these limitations, we propose an agentic divide-and-conquer framework that (i) offloads parsing to an external tool to construct an abstract syntax tree (AST) and (ii) enforces recursive reasoning over each intermediate sub-expression with focused context. This framework reliably mitigates deep-composition failures, achieving substantial performance improvement at large depths (e.g., F1-Score $= 1.0$ at depth $100$).

General Machine Learning · Hardware and Software

Lei Gao, Chaoyi Jiang, Hossein Entezari Zarch, Daniel Wong, Mark D. HIll, Murali Annavaram

Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive prefill and memory-bound decode phases. Existing approaches either (1) aggregate both phases on shared GPUs, leading to interference between prefill and decode phases, which degrades Time-Between-Tokens (TBT); or (2) disaggregate the two phases across GPUs, improving latency but wasting resources through duplicated models and KV cache transfers. We present DuetServe, a unified LLM serving framework that achieves disaggregation-level isolation within a single GPU. DuetServe operates in aggregated mode by default and dynamically activates SM-level GPU spatial multiplexing when TBT degradation is predicted. Its key idea is to decouple prefill and decode execution only when needed through fine-grained, adaptive SM partitioning that provides phase isolation only when contention threatens latency service level objectives. DuetServe integrates (1) an attention-aware roofline model to forecast iteration latency, (2) a partitioning optimizer that selects the optimal SM split to maximize throughput under TBT constraints, and (3) an interruption-free execution engine that eliminates CPU–GPU synchronization overhead. Evaluations show that DuetServe improves total throughput by up to 1.3× while maintaining low generation latency compared to state-of-the-art frameworks.

Deep Learning · Large Language Models

Jia Liu, Jiaxin Luo, Xinhao Qiu, Yixue Hao, Min Chen

Magnitude-based stability proxies such as parameter drift are widely used in narrow-task fine-tuning, yet they do not reliably indicate degradation of broad capabilities. We identify trajectory lock-in: under fixed training conditions for narrow adaptation, the joint evolution of task loss and broad generalization collapses onto a shared low-dimensional degradation curve, so many stabilizers primarily change the rate of progress along this curve rather than altering the curve itself. This yields a drift paradox, in which comparable Euclidean displacement can still correspond to divergent generalization outcomes. To diagnose the underlying structure, we introduce objective-agnostic geometric probes that track the effective update subspace, together with an online harm signal that reflects curvature-dominated channeling toward directions associated with broad degradation. Finally, we show that escaping lock-in requires a spectral bifurcation, namely a qualitative reorientation of the update subspace toward softer curvature modes, thereby improving broad generalization while maintaining matched training performance. We validate these findings across model scales and modalities in narrow-task settings, and report practical deployment procedures and overhead measurements.

Deep Learning · Large Language Models

Kejun Liu, Yuanyuan Liu, Ke Wang, Zhe Chen, Yibing Zhan, Wei Xiang, Hongyan Zhang

Multimodal Large Language Models (MLLMs) show promise for Multimodal Emotion Recognition (MER) but often remain unreliable because sparse emotional cues could be easily overwhelmed and affected by redundant context. While fine-tuning is effective, it is usually costly when using large models. Training-free methods like chain-of-thought reasoning provide a practical alternative, but they mostly rely on heuristic prompting to influence the model behaviors and do not explicitly focus on emotion relevant tokens internally, which would allow decision-relevant emotional tokens to be diluted by environmental noise, resulting in unstable predictions. To address this limitation without training, we rethink MER from a world-model perspective that treats emotion as a latent state inferred from noisy and redundant multimodal observations. Under frozen parameters, this view suggests that robustness depends on constraining why and how tokens contribute to inference. Based on this insight, we propose WETR (World-Model inspired Emotion-aware Token Refinement), a training-free, plug-and-play regulator that reshapes token usage through two mechanisms: Noise-suppressed Token Selection (NTS), which suppresses redundant intra-modal noise, and State-strengthened Token Reweighting (STR), which amplifies decision-relevant emotional tokens. Experiments on multiple MER benchmarks demonstrate that WETR consistently improves accuracy and stability under frozen parameters, which also improves token-level interpretability.

Theory · Reinforcement Learning and Planning

Ruiquan Huang, Donghao Li, Yingbin LIANG, Jing Yang

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL algorithms achieve favorable sample complexity, but often rely on computationally intractable oracles. In this paper, we use supervised learning as a computational proxy to establish a clear hierarchy of commonly adopted RL oracles under low-rank Markov Decision Processes (MDPs). This hierarchy shows that policy evaluation is the most computationally efficient oracle, provided that supervised learning can be efficiently solved. Motivated by this observation, we propose a novel optimistic actor–critic algorithm that relies solely on the policy evaluation oracle. We prove that our algorithm outperforms the existing sample complexity guarantees for low-rank MDPs while avoiding computationally expensive planning or optimization oracles commonly assumed in prior works. We further extend our theoretical results to approximately low-rank MDPs and demonstrate that this setting captures a broad class of real-world environments. Finally, we validate our theoretical results with experiments on several standard Gym benchmarks.