{"total":176,"rows":[{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81,"area":"wm"},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47,"area":null},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2509.15207","title":"FlowRL: Matching Reward Distributions for LLM Reasoning","created":"2025-09-18","cited_by_count":40,"area":"lr"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2307.08875","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","created":"2023-07-17","cited_by_count":36,"area":null},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2301.13589","title":"Policy Gradient for Rectangular Robust Markov Decision Processes","created":"2023-01-31","cited_by_count":31,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"area":null},{"id":"2405.13629","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","created":"2024-05-22","cited_by_count":26,"area":"deeprl"},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"},{"id":"2110.10117","title":"Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization","created":"2021-10-19","cited_by_count":25,"area":null},{"id":"2510.00037","title":"RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations","created":"2025-09-26","cited_by_count":25,"area":"vla"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2104.08381","title":"Robust Object Detection via Instance-Level Temporal Cycle Confusion","created":"2021-04-16","cited_by_count":24,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2103.11575","title":"Learn-to-Race: A Multimodal Control Environment for Autonomous Racing","created":"2021-03-22","cited_by_count":23,"area":null},{"id":"2301.00858","title":"Robust Average-Reward Markov Decision Processes","created":"2023-01-02","cited_by_count":22,"area":null},{"id":"2407.13709","title":"Understanding Reference Policies in Direct Preference Optimization","created":"2024-07-18","cited_by_count":22,"area":"alignment"},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2410.20254","title":"Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL","created":"2024-10-26","cited_by_count":21,"area":"deeprl"},{"id":"2205.14327","title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2501.06148","title":"From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training","created":"2025-01-10","cited_by_count":19,"area":"diffusion"},{"id":"2405.00987","title":"S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic","created":"2024-05-02","cited_by_count":18,"area":"deeprl"},{"id":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"id":"2501.17827","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","created":"2025-01-29","cited_by_count":17,"area":"deeprl"},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2210.00999","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"id":"2210.01801","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2305.17109","title":"Reinforcement Learning with Simple Sequence Priors","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2206.06841","title":"Robust Reinforcement Learning with Distributional Risk-averse formulation","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2209.10187","title":"On the convex formulations of robust Markov decision processes","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2109.03188","title":"Optimizing Quantum Variational Circuits with Deep Reinforcement Learning","created":"2021-09-07","cited_by_count":9,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"area":null},{"id":"2310.18127","title":"Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models","created":"2023-10-27","cited_by_count":9,"area":"lr"},{"id":"2212.01174","title":"Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning","created":"2022-12-02","cited_by_count":8,"area":null},{"id":"2305.10411","title":"Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2309.01107","title":"Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization","created":"2023-09-03","cited_by_count":8,"area":null},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2205.10316","title":"Complex behavior from intrinsic motivation to occupy action-state path space","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2207.02016","title":"Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization","created":"2022-07-05","cited_by_count":7,"area":null},{"id":"2212.11746","title":"Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-22","cited_by_count":7,"area":null},{"id":"2307.14316","title":"Reinforcement Learning by Guided Safe Exploration","created":"2023-07-26","cited_by_count":7,"area":null},{"id":"2312.06436","title":"Reward Certification for Policy Smoothed Reinforcement Learning","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2312.08751","title":"Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\\infty$ Lipschitz Policy Networks","created":"2023-12-14","cited_by_count":7,"area":null},{"id":"2506.05615","title":"When Maximum Entropy Misleads Policy Optimization","created":"2025-06-05","cited_by_count":7,"area":"deeprl"},{"id":"2512.04748","title":"Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time","created":"2025-12-04","cited_by_count":7,"area":"lr"},{"id":"2201.12434","title":"Do You Need the Entropy Reward (in Practice)?","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2204.05263","title":"Maximum entropy optimal density control of discrete-time linear systems and Schr\\\"odinger bridges","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2204.09424","title":"SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2301.13642","title":"An Efficient Solution to s-Rectangular Robust Markov Decision Processes","created":"2023-01-31","cited_by_count":6,"area":null},{"id":"2302.10831","title":"Minimax-Bayes Reinforcement Learning","created":"2023-02-21","cited_by_count":6,"area":null},{"id":"2310.09833","title":"Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization","created":"2023-10-15","cited_by_count":6,"area":null},{"id":"2402.09992","title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2402.14174","title":"Blending Data-Driven Priors in Dynamic Games","created":"2024-02-21","cited_by_count":6,"area":null},{"id":"2406.03995","title":"AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control","created":"2024-06-06","cited_by_count":6,"area":"deeprl"},{"id":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2501.09080","title":"Average-Reward Soft Actor-Critic","created":"2025-01-15","cited_by_count":6,"area":"deeprl"},{"id":"2502.17322","title":"TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control","created":"2025-02-24","cited_by_count":6,"area":"deeprl"},{"id":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"id":"2510.11711","title":"Reinforced sequential Monte Carlo for amortised sampling","created":"2025-10-13","cited_by_count":6,"area":null},{"id":"2512.04359","title":"Efficient Reinforcement Learning with Semantic and Token Entropy for LLM Reasoning","created":"2025-12-04","cited_by_count":6,"area":"lr"},{"id":"2603.14389","title":"From $\\log \\pi$ to $\\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2406.08847","title":"Roping in Uncertainty: Robustness and Regularization in Markov Games","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2601.19969","title":"E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning","created":"2026-01-27","cited_by_count":5,"area":"deeprl"},{"id":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2305.09041","title":"What Matters in Reinforcement Learning for Tractography","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2406.18033","title":"Boosting Soft Q-Learning by Bounding","created":"2024-06-26","cited_by_count":4,"area":"deeprl"},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2503.13223","title":"Distributionally Robust Free Energy Principle for Decision-Making","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2508.20784","title":"Single Agent Robust Deep Reinforcement Learning for Bus Fleet Control","created":"2025-08-28","cited_by_count":4,"area":"deeprl"},{"id":"2207.05824","title":"Conditional Energy-Based Models for Implicit Policies: The Gap between Theory and Practice","created":"2022-07-12","cited_by_count":3,"area":null},{"id":"2303.02557","title":"Bounding the Optimal Value Function in Compositional Reinforcement Learning","created":"2023-03-05","cited_by_count":3,"area":null},{"id":"2303.04356","title":"Soft Actor-Critic Algorithm with Truly-satisfied Inequality Constraint","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2411.01827","title":"Risk-sensitive control as inference with R\\'enyi divergence","created":"2024-11-04","cited_by_count":3,"area":"deeprl"},{"id":"2501.17115","title":"Evidence on the Regularisation Properties of Maximum-Entropy Reinforcement Learning","created":"2025-01-28","cited_by_count":3,"area":"deeprl"}],"next_cursor":"100"}