{"list":"other","total":47,"rows":[{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"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":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"id":"2410.21845","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","created":"2024-10-29","cited_by_count":189},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"1612.03471","title":"Reinforcement Learning With Temporal Logic Rewards","created":"2016-12-11","cited_by_count":117},{"id":"1810.00950","title":"Omega-Regular Objectives in Model-Free Reinforcement Learning","created":"2018-09-26","cited_by_count":75},{"id":"1909.07299","title":"Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning","created":"2019-09-16","cited_by_count":75},{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74},{"id":"1807.06333","title":"Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications","created":"2018-07-17","cited_by_count":72},{"id":"2008.09293","title":"A Composable Specification Language for Reinforcement Learning Tasks","created":"2020-08-21","cited_by_count":69},{"id":"1609.07409","title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications","created":"2016-09-23","cited_by_count":67},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67},{"id":"2106.13687","title":"panda-gym: Open-source goal-conditioned environments for robotic learning","created":"2021-06-25","cited_by_count":59},{"id":"2509.15965","title":"RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation","created":"2025-09-19","cited_by_count":57},{"id":"2412.15544","title":"VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving","created":"2024-12-20","cited_by_count":51},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38},{"id":"2502.19908","title":"CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-scale Reinforcement Learning in Autonomous Driving","created":"2025-02-27","cited_by_count":34},{"id":"2102.00582","title":"Multi-Agent Reinforcement Learning with Temporal Logic Specifications","created":"2021-02-01","cited_by_count":27},{"id":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25},{"id":"2010.05150","title":"Safe Reinforcement Learning with Natural Language Constraints","created":"2020-10-11","cited_by_count":23},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19},{"id":"2305.01381","title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees","created":"2023-05-02","cited_by_count":18},{"id":"2201.12231","title":"Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications","created":"2022-01-28","cited_by_count":12},{"id":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10},{"id":"2412.03012","title":"Learning Whole-Body Loco-Manipulation for Omni-Directional Task Space Pose Tracking with a Wheeled-Quadrupedal-Manipulator","created":"2024-12-04","cited_by_count":10},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9},{"id":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9},{"id":"2505.00562","title":"TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching","created":"2025-05-01","cited_by_count":9},{"id":"2306.06808","title":"Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications","created":"2023-06-11","cited_by_count":7},{"id":"2510.00225","title":"TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks","created":"2025-09-30","cited_by_count":6},{"id":"2206.13754","title":"DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems","created":"2022-06-28","cited_by_count":3},{"id":"2506.16396","title":"GoalLadder: Incremental Goal Discovery with Vision-Language Models","created":"2025-06-19","cited_by_count":3},{"id":"2303.01346","title":"Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications","created":"2023-03-02","cited_by_count":2},{"id":"2303.14061","title":"Learning Reward Machines in Cooperative Multi-Agent Tasks","created":"2023-03-24","cited_by_count":2},{"id":"2401.02991","title":"GLIDE-RL: Grounded Language Instruction through DEmonstration in RL","created":"2024-01-03","cited_by_count":2},{"id":"2505.10010","title":"ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts","created":"2025-05-15","cited_by_count":2},{"id":"2505.12107","title":"Learning Probabilistic Temporal Logic Specifications for Stochastic Systems","created":"2025-05-17","cited_by_count":2},{"id":"2510.19562","title":"DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning","created":"2025-10-22","cited_by_count":1},{"id":"2511.02304","title":"Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning","created":"2025-11-04","cited_by_count":1}],"next_cursor":null}