{"total":62,"rows":[{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327,"area":null},{"id":"2210.07105","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","created":"2022-10-13","cited_by_count":119,"area":"offlinerl"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2303.17503","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","created":"2023-03-29","cited_by_count":51,"area":null},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2504.17838","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards","created":"2025-04-24","cited_by_count":35,"area":"deeprl"},{"id":"2410.03654","title":"Learning Humanoid Locomotion over Challenging Terrain","created":"2024-10-04","cited_by_count":26,"area":null},{"id":"2406.12905","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","created":"2024-06-11","cited_by_count":24,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","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":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2506.03404","title":"The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks","created":"2025-06-03","cited_by_count":13,"area":"deeprl"},{"id":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","cited_by_count":12,"area":"deeprl"},{"id":"2511.19584","title":"Learning Massively Multitask World Models for Continuous Control","created":"2025-11-24","cited_by_count":12,"area":"wm"},{"id":"2310.13396","title":"RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2310.00036","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2209.10901","title":"Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2310.05205","title":"GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2510.01764","title":"Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX","created":"2025-10-02","cited_by_count":5,"area":"deeprl"},{"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":"2306.03530","title":"RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2405.11432","title":"On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks","created":"2024-05-19","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":"2305.04180","title":"Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity","created":"2023-05-07","cited_by_count":3,"area":null},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2309.16743","title":"High Throughput Training of Deep Surrogates from Large Ensemble Runs","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2409.18827","title":"ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning","created":"2024-09-27","cited_by_count":3,"area":"deeprl"},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2211.13260","title":"Actively Learning Costly Reward Functions for Reinforcement Learning","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2302.01399","title":"Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning","created":"2023-02-02","cited_by_count":2,"area":null},{"id":"2401.03993","title":"Behavioural Cloning in VizDoom","created":"2024-01-08","cited_by_count":2,"area":"offlinerl"},{"id":"2404.16364","title":"ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2406.01939","title":"Speeding up Policy Simulation in Supply Chain RL","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2501.12620","title":"Adaptive Data Exploitation in Deep Reinforcement Learning","created":"2025-01-22","cited_by_count":1,"area":"deeprl"},{"id":"2501.12703","title":"HEPPO-GAE: Hardware-Efficient Proximal Policy Optimization with Generalized Advantage Estimation","created":"2025-01-22","cited_by_count":1,"area":"deeprl"},{"id":"2508.18258","title":"ANO : Faster is Better in Noisy Landscape","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2606.20411","title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2606.28433","title":"Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy","created":"2026-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2310.05430","title":"Replication of Multi-agent Reinforcement Learning for the \"Hide and Seek\" Problem","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2409.04971","title":"Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients","created":"2024-09-08","cited_by_count":0,"area":"deeprl"},{"id":"2507.10990","title":"Adaptive Policy Synchronization for Scalable Reinforcement Learning","created":"2025-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2602.09726","title":"ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm","created":"2026-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2603.01260","title":"MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration","created":"2026-03-01","cited_by_count":0,"area":"agents"},{"id":"2603.12145","title":"Automatic Generation of High-Performance RL Environments","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2604.27162","title":"A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.02320","title":"ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields","created":"2026-05-04","cited_by_count":0,"area":"alignment"},{"id":"2606.15846","title":"FlashNav: Training Deployable Robot Navigation Policies in Seconds","created":"2026-06-14","cited_by_count":0,"area":"deeprl"},{"id":"2606.21587","title":"FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving","created":"2026-06-19","cited_by_count":0,"area":"driving"},{"id":"2608.07335","title":"A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.09059","title":"PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.13243","title":"GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo","created":"2026-09-03","cited_by_count":0,"area":"deeprl"},{"id":"2609.19850","title":"GR2PO: Group Relative Return Policy Optimization for Continuous Robot Control","created":"2026-09-17","cited_by_count":0,"area":"deeprl"},{"id":"2610.04638","title":"Policy as Data: Replay-Based Policy Dual Averaging via Advantage Regression","created":"2026-10-03","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}