{"list":"other","total":60,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"2402.08191","title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","created":"2024-02-13","cited_by_count":133},{"id":"2103.14295","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","created":"2021-03-26","cited_by_count":116},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112},{"id":"2202.02215","title":"A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective","created":"2022-02-04","cited_by_count":105},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90},{"id":"1809.07731","title":"Benchmarking Reinforcement Learning Algorithms on Real-World Robots","created":"2018-09-20","cited_by_count":65},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"2006.09484","title":"Partial Policy Iteration for L1-Robust Markov Decision Processes","created":"2020-06-16","cited_by_count":50},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50},{"id":"1902.08708","title":"Distributionally Robust Reinforcement Learning","created":"2019-02-23","cited_by_count":42},{"id":"2003.02894","title":"Distributional Robustness and Regularization in Reinforcement Learning","created":"2020-03-05","cited_by_count":40},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38},{"id":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36},{"id":"1811.06032","title":"Natural Environment Benchmarks for Reinforcement Learning","created":"2018-11-14","cited_by_count":32},{"id":"2007.07176","title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","created":"2020-07-14","cited_by_count":30},{"id":"2105.08541","title":"DACBench: A Benchmark Library for Dynamic Algorithm Configuration","created":"2021-05-18","cited_by_count":28},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26},{"id":"2307.07907","title":"Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation","created":"2023-07-15","cited_by_count":25},{"id":"2009.11459","title":"Robust Finite-State Controllers for Uncertain POMDPs","created":"2020-09-24","cited_by_count":24},{"id":"2212.02705","title":"What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?","created":"2022-12-06","cited_by_count":22},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21},{"id":"2405.01677","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","created":"2024-05-02","cited_by_count":21},{"id":"2109.08776","title":"Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations","created":"2021-09-17","cited_by_count":12},{"id":"2211.03413","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","created":"2022-11-07","cited_by_count":11},{"id":"2310.04323","title":"Adjustable Robust Reinforcement Learning for Online 3D Bin Packing","created":"2023-10-06","cited_by_count":10},{"id":"2405.16390","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-05-26","cited_by_count":9},{"id":"2206.07188","title":"Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising","created":"2022-06-14","cited_by_count":8},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8},{"id":"2306.06136","title":"Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents","created":"2023-06-09","cited_by_count":7},{"id":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","cited_by_count":5}],"next_cursor":null}