{"total":88,"rows":[{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"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":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2408.15099","title":"No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery","created":"2024-08-27","cited_by_count":31,"area":"deeprl"},{"id":"2511.16652","title":"Evolution Strategies at the Hyperscale","created":"2025-11-20","cited_by_count":25,"area":null},{"id":"2412.08021","title":"Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning","created":"2024-12-11","cited_by_count":21,"area":"deeprl"},{"id":"2605.21800","title":"stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation","created":"2026-05-20","cited_by_count":20,"area":"wm"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2502.05453","title":"LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning","created":"2025-02-08","cited_by_count":18,"area":"agents"},{"id":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2504.12714","title":"Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination","created":"2025-04-17","cited_by_count":14,"area":null},{"id":"2502.01591","title":"Improving Transformer World Models for Data-Efficient RL","created":"2025-02-03","cited_by_count":13,"area":"wm"},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2412.17113","title":"Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps","created":"2024-12-22","cited_by_count":11,"area":"deeprl"},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2405.19548","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","created":"2024-05-29","cited_by_count":10,"area":"deeprl"},{"id":"2505.20659","title":"An Optimisation Framework for Unsupervised Environment Design","created":"2025-05-27","cited_by_count":10,"area":"deeprl"},{"id":"2510.12088","title":"One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration","created":"2025-10-14","cited_by_count":10,"area":"wm"},{"id":"2408.12525","title":"PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators","created":"2024-08-22","cited_by_count":7,"area":"deeprl"},{"id":"2409.12798","title":"Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2508.00046","title":"Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains","created":"2025-07-31","cited_by_count":7,"area":"deeprl"},{"id":"2409.00853","title":"JaxLife: An Open-Ended Agentic Simulator","created":"2024-09-01","cited_by_count":6,"area":"agents"},{"id":"2502.11537","title":"Simulus: Combining Improvements in Sample-Efficient World Model Agents","created":"2025-02-17","cited_by_count":6,"area":"wm"},{"id":"2609.16074","title":"World-Action Models for Robot Learning and Control: A Survey","created":"2026-09-13","cited_by_count":6,"area":"wm"},{"id":"2507.17668","title":"How Should We Meta-Learn Reinforcement Learning Algorithms?","created":"2025-07-23","cited_by_count":5,"area":"deeprl"},{"id":"2509.00338","title":"Scalable Option Learning in High-Throughput Environments","created":"2025-08-30","cited_by_count":5,"area":"deeprl"},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"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":"2407.03969","title":"Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2508.16821","title":"PuzzleJAX: A Benchmark for Reasoning and Learning","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2508.12480","title":"The Yokai Learning Environment: Tracking Beliefs Over Space and Time","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2508.15679","title":"An Efficient Open World Environment for Multi-Agent Social Learning","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2511.16592","title":"gfnx: Fast and Scalable Library for Generative Flow Networks in JAX","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2407.14516","title":"RobocupGym: A challenging continuous control benchmark in Robocup","created":"2024-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2504.17490","title":"Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning","created":"2025-04-24","cited_by_count":2,"area":"deeprl"},{"id":"2505.11962","title":"CrafText Benchmark: Advancing Instruction Following in Complex Multimodal Open-Ended World","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2505.21236","title":"Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies","created":"2025-05-27","cited_by_count":2,"area":"deeprl"},{"id":"2506.20061","title":"Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.05561","title":"Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2511.04904","title":"Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2603.02008","title":"Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards","created":"2026-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2603.23129","title":"Polaris: A G\\\"odel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2606.08340","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","created":"2026-06-06","cited_by_count":2,"area":"agents"},{"id":"2606.20376","title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","created":"2026-06-18","cited_by_count":2,"area":"deeprl"},{"id":"2406.00424","title":"A Batch Sequential Halving Algorithm without Performance Degradation","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2410.22165","title":"EconoJax: A Fast & Scalable Economic Simulation in Jax","created":"2024-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2503.06101","title":"ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning","created":"2025-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.13530","title":"CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter","created":"2025-08-19","cited_by_count":1,"area":"agents"},{"id":"2508.15693","title":"NiceWebRL: a Python library for human subject experiments with reinforcement learning environments","created":"2025-08-21","cited_by_count":1,"area":"alignment"},{"id":"2510.18221","title":"The Emergence of Complex Behavior in Large-Scale Ecological Environments","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2603.09090","title":"Overcoming Valid Action Suppression in Unmasked Policy Gradient Algorithms","created":"2026-03-10","cited_by_count":1,"area":"deeprl"},{"id":"2605.06869","title":"Agentick: A Unified Benchmark for General Sequential Decision-Making Agents","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2606.31700","title":"Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks","created":"2026-06-30","cited_by_count":1,"area":"deeprl"},{"id":"2506.22609","title":"Ludax: A GPU-Accelerated Domain Specific Language for Board Games","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2509.22008","title":"Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.15378","title":"Terra Nova: A Comprehensive Challenge Environment for Intelligent Agents","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2511.18987","title":"Dynamic Mixture of Experts Against Severe Distribution Shifts","created":"2025-11-24","cited_by_count":0,"area":"moe"},{"id":"2601.14232","title":"KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.23156","title":"Unsupervised Hierarchical Skill Discovery","created":"2026-01-30","cited_by_count":0,"area":"deeprl"},{"id":"2602.01665","title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.19964","title":"On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.12145","title":"Automatic Generation of High-Performance RL Environments","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.01131","title":"Forager: a lightweight testbed for continual learning with partial observability in RL","created":"2026-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.01358","title":"PACE: Parameter Change for Unsupervised Environment Design","created":"2026-05-02","cited_by_count":0,"area":"deeprl"},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2606.00880","title":"Task diversity produces systematic transfer but inhibits continual reinforcement learning","created":"2026-05-30","cited_by_count":0,"area":"deeprl"},{"id":"2606.03382","title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.29577","title":"DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.09902","title":"DSLE: A Learning Environment for Dark Souls Boss Encounters","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14642","title":"Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions","created":"2026-07-29","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":"2609.34214","title":"GlyphBench: A Playground for Language-Model Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36052","title":"PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.38065","title":"Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2609.38598","title":"Reinforcement Learning with Complex (valued) Memories","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2610.04604","title":"Anticipating the Consequences of Curriculum Decisions with Large Language Models","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05569","title":"Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.13002","title":"Scaling Empowered Agents","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13504","title":"Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning","created":"2026-10-09","cited_by_count":0,"area":"wm"},{"id":"2610.14186","title":"Visualizing the World Model in an Agent's Value Function","created":"2026-10-09","cited_by_count":0,"area":"wm"},{"id":"2610.14807","title":"ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.15328","title":"Anchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}