{"total":474,"rows":[{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293,"area":"offlinerl"},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325,"area":"diffusion"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90,"area":"offlinerl"},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61,"area":"driving"},{"id":"2409.10164","title":"Quantile Regression for Distributional Reward Models in RLHF","created":"2024-09-16","cited_by_count":60,"area":"alignment"},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","cited_by_count":53,"area":null},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2111.03947","title":"Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2021-11-06","cited_by_count":43,"area":null},{"id":"2205.05138","title":"Efficient Risk-Averse Reinforcement Learning","created":"2022-05-10","cited_by_count":43,"area":null},{"id":"2402.02651","title":"Vision-Language Models Provide Promptable Representations for Reinforcement Learning","created":"2024-02-05","cited_by_count":41,"area":"mllm"},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37,"area":null},{"id":"2110.09796","title":"Offline Reinforcement Learning with Value-based Episodic Memory","created":"2021-10-19","cited_by_count":36,"area":"offlinerl"},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2102.08159","title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","created":"2021-02-16","cited_by_count":31,"area":null},{"id":"2301.04462","title":"An Analysis of Quantile Temporal-Difference Learning","created":"2023-01-11","cited_by_count":31,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2104.08977","title":"Off-Policy Risk Assessment in Contextual Bandits","created":"2021-04-18","cited_by_count":29,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2302.05793","title":"Distributional GFlowNets with Quantile Flows","created":"2023-02-11","cited_by_count":28,"area":null},{"id":"2103.02828","title":"STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation","created":"2021-03-04","cited_by_count":27,"area":null},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27,"area":null},{"id":"2111.04714","title":"A Dataset Perspective on Offline Reinforcement Learning","created":"2021-11-08","cited_by_count":27,"area":"offlinerl"},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2102.07936","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26,"area":"offlinerl"},{"id":"2210.05650","title":"Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2022-10-11","cited_by_count":26,"area":null},{"id":"2310.05858","title":"Distributional Soft Actor-Critic with Three Refinements","created":"2023-10-09","cited_by_count":25,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23,"area":"offlinerl"},{"id":"2103.00083","title":"Flexible Model Aggregation for Quantile Regression","created":"2021-02-26","cited_by_count":22,"area":null},{"id":"2110.13578","title":"Distributional Reinforcement Learning for Multi-Dimensional Reward Functions","created":"2021-10-26","cited_by_count":22,"area":null},{"id":"2303.16585","title":"Quantum Deep Hedging","created":"2023-03-29","cited_by_count":22,"area":null},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","cited_by_count":21,"area":null},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2302.09456","title":"Distributional Offline Policy Evaluation with Predictive Error Guarantees","created":"2023-02-19","cited_by_count":20,"area":"diffusion"},{"id":"2303.03747","title":"Graph Decision Transformer","created":"2023-03-07","cited_by_count":20,"area":"offlinerl"},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2311.01753","title":"RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization","created":"2023-11-03","cited_by_count":20,"area":null},{"id":"2110.03375","title":"Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning","created":"2021-10-07","cited_by_count":18,"area":null},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2105.10266","title":"Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving","created":"2021-05-21","cited_by_count":17,"area":"driving"},{"id":"2402.08530","title":"A Distributional Analogue to the Successor Representation","created":"2024-02-13","cited_by_count":17,"area":"deeprl"},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2409.00328","title":"Foundations of Multivariate Distributional Reinforcement Learning","created":"2024-08-31","cited_by_count":17,"area":"deeprl"},{"id":"2101.08477","title":"Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment","created":"2021-01-21","cited_by_count":16,"area":null},{"id":"2105.11366","title":"GMAC: A Distributional Perspective on Actor-Critic Framework","created":"2021-05-24","cited_by_count":16,"area":null},{"id":"2210.14051","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"area":"deeprl"},{"id":"2102.11075","title":"SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2104.03111","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2105.06696","title":"Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning","created":"2021-05-14","cited_by_count":15,"area":null},{"id":"2112.04643","title":"Autoregressive Quantile Flows for Predictive Uncertainty Estimation","created":"2021-12-09","cited_by_count":15,"area":null},{"id":"2309.07051","title":"UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons","created":"2023-09-13","cited_by_count":15,"area":"diffusion"},{"id":"2406.12563","title":"A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo","created":"2024-06-18","cited_by_count":15,"area":"deeprl"},{"id":"2409.15844","title":"Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection","created":"2024-09-24","cited_by_count":15,"area":null},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"area":null},{"id":"2206.06711","title":"Conformal Off-policy Prediction","created":"2022-06-14","cited_by_count":14,"area":null},{"id":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14,"area":"offlinerl"},{"id":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2102.03119","title":"Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning","created":"2021-02-05","cited_by_count":13,"area":"driving"},{"id":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","cited_by_count":13,"area":null},{"id":"2207.07467","title":"Deep Hedging: Continuous Reinforcement Learning for Hedging of General Portfolios across Multiple Risk Aversions","created":"2022-07-15","cited_by_count":13,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2305.12751","title":"Testing of Deep Reinforcement Learning Agents with Surrogate Models","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2407.00401","title":"PUZZLES: A Benchmark for Neural Algorithmic Reasoning","created":"2024-06-29","cited_by_count":13,"area":null},{"id":"2107.11722","title":"Learning Risk-aware Costmaps for Traversability in Challenging Environments","created":"2021-07-25","cited_by_count":12,"area":null},{"id":"2109.08776","title":"Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations","created":"2021-09-17","cited_by_count":12,"area":null}],"next_cursor":"100"}