{"total":34,"rows":[{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2202.05780","title":"A Modern Self-Referential Weight Matrix That Learns to Modify Itself","created":"2022-02-11","cited_by_count":41,"area":null},{"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,"area":null},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38,"area":null},{"id":"2203.11889","title":"Insights From the NeurIPS 2021 NetHack Challenge","created":"2022-03-22","cited_by_count":20,"area":null},{"id":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2305.19044","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","created":"2023-05-30","cited_by_count":19,"area":null},{"id":"2208.06399","title":"AutoShard: Automated Embedding Table Sharding for Recommender Systems","created":"2022-08-12","cited_by_count":17,"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":"2110.10661","title":"SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark","created":"2021-10-20","cited_by_count":11,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2210.00066","title":"Improving Policy Learning via Language Dynamics Distillation","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2311.03736","title":"Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7,"area":null},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"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":"2209.10055","title":"Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games","created":"2022-09-21","cited_by_count":4,"area":null},{"id":"2212.00253","title":"Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2102.13565","title":"Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision","created":"2021-02-26","cited_by_count":3,"area":null},{"id":"2102.04220","title":"Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2104.06630","title":"A Novel Approach to Curiosity and Explainable Reinforcement Learning via Interpretable Sub-Goals","created":"2021-04-14","cited_by_count":2,"area":null},{"id":"2109.02631","title":"Guiding Global Placement With Reinforcement Learning","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2110.06477","title":"Feudal Reinforcement Learning by Reading Manuals","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2307.08532","title":"LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents","created":"2023-07-17","cited_by_count":0,"area":null},{"id":"2308.15802","title":"Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMO","created":"2023-08-30","cited_by_count":0,"area":null},{"id":"2310.03161","title":"Neural architecture impact on identifying temporally extended Reinforcement Learning tasks","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2602.08517","title":"TreeTensor: Boost AI System on Nested Data with Constrained Tree-Like Tensor","created":"2026-02-09","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}],"next_cursor":null}