{"total":81,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566,"area":null},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109,"area":null},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2107.02053","title":"MixStyle Neural Networks for Domain Generalization and Adaptation","created":"2021-07-05","cited_by_count":64,"area":null},{"id":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2504.09710","title":"DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training","created":"2025-04-13","cited_by_count":46,"area":"lr"},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2105.02993","title":"Learning Controllable Content Generators","created":"2021-05-06","cited_by_count":40,"area":null},{"id":"2206.04199","title":"Deep Surrogate Assisted Generation of Environments","created":"2022-06-09","cited_by_count":40,"area":null},{"id":"2103.04847","title":"Adversarial Reinforcement Learning for Procedural Content Generation","created":"2021-03-08","cited_by_count":36,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"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":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2102.08370","title":"Quantifying the effects of environment and population diversity in multi-agent reinforcement learning","created":"2021-02-16","cited_by_count":22,"area":null},{"id":"2210.04839","title":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2103.09815","title":"TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2305.06436","title":"Multi-Robot Coordination and Layout Design for Automated Warehousing","created":"2023-05-10","cited_by_count":17,"area":null},{"id":"2404.15538","title":"DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft","created":"2024-04-23","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":"2202.10608","title":"It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation","created":"2022-02-22","cited_by_count":14,"area":null},{"id":"2506.04287","title":"Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback","created":"2025-06-04","cited_by_count":12,"area":"agents"},{"id":"2406.03997","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","created":"2024-06-06","cited_by_count":11,"area":"deeprl"},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2310.18622","title":"Arbitrarily Scalable Environment Generators via Neural Cellular Automata","created":"2023-10-28","cited_by_count":9,"area":null},{"id":"2301.06629","title":"Diverse Multimedia Layout Generation with Multi Choice Learning","created":"2023-01-16","cited_by_count":8,"area":null},{"id":"2105.14780","title":"Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning","created":"2021-05-31","cited_by_count":7,"area":null},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2012.02527","title":"Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments","created":"2020-12-04","cited_by_count":6,"area":"offlinerl"},{"id":"2104.06106","title":"Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution","created":"2021-04-13","cited_by_count":6,"area":null},{"id":"2106.10365","title":"Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2203.10941","title":"Transfer Dynamics in Emergent Evolutionary Curricula","created":"2022-03-03","cited_by_count":6,"area":null},{"id":"2503.16799","title":"Causally Aligned Curriculum Learning","created":"2025-03-21","cited_by_count":6,"area":"deeprl"},{"id":"2306.16978","title":"Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2407.13513","title":"Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization","created":"2024-07-18","cited_by_count":5,"area":"deeprl"},{"id":"2104.10610","title":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2302.01561","title":"Hierarchically Composing Level Generators for the Creation of Complex Structures","created":"2023-02-03","cited_by_count":4,"area":null},{"id":"2309.12815","title":"Improving Generalization in Game Agents with Data Augmentation in Imitation Learning","created":"2023-09-22","cited_by_count":4,"area":"offlinerl"},{"id":"2508.16821","title":"PuzzleJAX: A Benchmark for Reasoning and Learning","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2509.13341","title":"Imagined Autocurricula","created":"2025-09-11","cited_by_count":4,"area":"wm"},{"id":"2407.04221","title":"Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents","created":"2024-07-05","cited_by_count":3,"area":"offlinerl"},{"id":"2409.17469","title":"VertiSelector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain","created":"2024-09-26","cited_by_count":3,"area":"deeprl"},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2309.05371","title":"Exploring Minecraft Settlement Generators with Generative Shift Analysis","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2406.01952","title":"Improving Generalization in Aerial and Terrestrial Mobile Robots Control Through Delayed Policy Learning","created":"2024-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2406.04920","title":"Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning","created":"2024-06-07","cited_by_count":2,"area":"deeprl"},{"id":"2102.07266","title":"Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning","created":"2021-02-14","cited_by_count":1,"area":null},{"id":"2105.08568","title":"Fixed $\\beta$-VAE Encoding for Curious Exploration in Complex 3D Environments","created":"2021-05-18","cited_by_count":1,"area":null},{"id":"2210.09026","title":"WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2305.18553","title":"Controllable Path of Destruction","created":"2023-05-29","cited_by_count":1,"area":null},{"id":"2311.00651","title":"Emergence of Collective Open-Ended Exploration from Decentralized Meta-Reinforcement Learning","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2401.09258","title":"Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2409.13886","title":"Learning to Play Video Games with Intuitive Physics Priors","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2501.02481","title":"Representation Convergence: Mutual Distillation is Secretly a Form of Regularization","created":"2025-01-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.17384","title":"A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning","created":"2025-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2503.08061","title":"ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2509.21234","title":"AbideGym: Turning Static RL Worlds into Adaptive Challenges","created":"2025-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2108.09478","title":"MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl","created":"2021-08-21","cited_by_count":0,"area":null},{"id":"2112.08369","title":"Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2204.06550","title":"Improving generalization to new environments and removing catastrophic forgetting in Reinforcement Learning by using an eco-system of agents","created":"2022-04-13","cited_by_count":0,"area":null},{"id":"2212.06451","title":"Improving generalization in reinforcement learning through forked agents","created":"2022-12-13","cited_by_count":0,"area":null},{"id":"2401.15856","title":"The Indoor-Training Effect: unexpected gains from distribution shifts in the transition function","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2412.16970","title":"A Research Agenda for Usability and Generalisation in Reinforcement Learning","created":"2024-12-22","cited_by_count":0,"area":"deeprl"},{"id":"2508.12356","title":"Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data","created":"2025-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2510.00690","title":"ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2510.15120","title":"Procedural Game Level Design with Deep Reinforcement Learning","created":"2025-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2602.18856","title":"Issues with Measuring Task Complexity via Random Policies in Robotic Tasks","created":"2026-02-21","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}],"next_cursor":null}