{"total":31,"rows":[{"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":"2511.16652","title":"Evolution Strategies at the Hyperscale","created":"2025-11-20","cited_by_count":25,"area":null},{"id":"2504.12714","title":"Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination","created":"2025-04-17","cited_by_count":14,"area":null},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"area":null},{"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":"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":"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":"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":"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":"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":"2603.23129","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":"2406.00424","title":"A Batch Sequential Halving Algorithm without Performance Degradation","created":"2024-06-01","cited_by_count":1,"area":null},{"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":"2510.18221","title":"The Emergence of Complex Behavior in Large-Scale Ecological Environments","created":"2025-10-21","cited_by_count":1,"area":null},{"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":"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":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"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":"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":"2610.04604","title":"Anticipating the Consequences of Curriculum Decisions with Large Language Models","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.13002","title":"Scaling Empowered Agents","created":"2026-10-09","cited_by_count":0,"area":null},{"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}