{"total":97,"rows":[{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410,"area":null},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2402.16801","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","created":"2024-02-26","cited_by_count":88,"area":"deeprl"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59,"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":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"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":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2402.03244","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","created":"2024-02-05","cited_by_count":26,"area":null},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"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":"2203.11889","title":"Insights From the NeurIPS 2021 NetHack Challenge","created":"2022-03-22","cited_by_count":20,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20,"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":"2211.15944","title":"The Effectiveness of World Models for Continual Reinforcement Learning","created":"2022-11-29","cited_by_count":17,"area":"wm"},{"id":"2403.00690","title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","created":"2024-03-01","cited_by_count":17,"area":"agents"},{"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":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2301.07799","title":"A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems","created":"2023-01-18","cited_by_count":13,"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":"2510.19788","title":"Benchmarking World-Model Learning with Environment-Level Queries","created":"2025-10-22","cited_by_count":10,"area":"wm"},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2206.00142","title":"IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2307.11922","title":"Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2311.05596","title":"LLM Augmented Hierarchical Agents","created":"2023-11-09","cited_by_count":9,"area":"agents"},{"id":"2407.17695","title":"Enhancing Agent Learning through World Dynamics Modeling","created":"2024-07-25","cited_by_count":9,"area":"agents"},{"id":"2503.01584","title":"SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models","created":"2025-03-03","cited_by_count":9,"area":"wm"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2301.12305","title":"Composing Task Knowledge with Modular Successor Feature Approximators","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2310.18144","title":"Improving Intrinsic Exploration by Creating Stationary Objectives","created":"2023-10-27","cited_by_count":7,"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":"2410.15221","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","created":"2024-10-19","cited_by_count":7,"area":"driving"},{"id":"2203.07454","title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2211.13051","title":"Powderworld: A Platform for Understanding Generalization via Rich Task Distributions","created":"2022-11-23","cited_by_count":6,"area":"wm"},{"id":"2509.00338","title":"Scalable Option Learning in High-Throughput Environments","created":"2025-08-30","cited_by_count":5,"area":"deeprl"},{"id":"2603.17621","title":"Complementary RL: Towards Efficient Experience-Driven Agent Learning","created":"2026-03-18","cited_by_count":5,"area":"agents"},{"id":"2607.01224","title":"AutoMem: Automated Learning of Memory as a Cognitive Skill","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2207.10218","title":"The Game of Hidden Rules: A New Kind of Benchmark Challenge for Machine Learning","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2302.10887","title":"The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning","created":"2023-01-21","cited_by_count":4,"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":"2407.12437","title":"Variable-Agnostic Causal Exploration for Reinforcement Learning","created":"2024-07-17","cited_by_count":4,"area":"deeprl"},{"id":"2205.00451","title":"The Ludii Game Description Language is Universal","created":"2022-05-01","cited_by_count":3,"area":null},{"id":"2205.13079","title":"Learning to Query Internet Text for Informing Reinforcement Learning Agents","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2602.00929","title":"Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents","created":"2026-01-31","cited_by_count":3,"area":"agents"},{"id":"2302.04693","title":"Scaling Goal-based Exploration via Pruning Proto-goals","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2306.17766","title":"Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules","created":"2023-06-30","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":"2408.11816","title":"Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction","created":"2024-08-21","cited_by_count":2,"area":"wm"},{"id":"2509.01793","title":"STORI: A Benchmark and Taxonomy for Stochastic Environments","created":"2025-09-01","cited_by_count":2,"area":"deeprl"},{"id":"2603.20209","title":"Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"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":"2308.15911","title":"Cyclophobic Reinforcement Learning","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2312.08463","title":"How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2410.03565","title":"Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2411.16262","title":"Probing for Consciousness in Machines","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2501.08925","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2503.12923","title":"Lifelong Reinforcement Learning with Similarity-Driven Weighting by Large Models","created":"2025-03-17","cited_by_count":1,"area":"deeprl"},{"id":"2503.18980","title":"CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning","created":"2025-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2505.02820","title":"AutoLibra: Agent Metric Induction from Open-Ended Human Feedback","created":"2025-05-05","cited_by_count":1,"area":"agents"},{"id":"2506.05577","title":"Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems","created":"2025-06-05","cited_by_count":1,"area":"agents"},{"id":"2506.11706","title":"Growing with Experience: Growing Neural Networks in Deep Reinforcement Learning","created":"2025-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2510.18483","title":"StarBench: A Turn-Based RPG Benchmark for Agentic Multimodal Decision-Making and Information Seeking","created":"2025-10-21","cited_by_count":1,"area":"agents"},{"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":"2605.20477","title":"Training Language Agents to Learn from Experience","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.17628","title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","created":"2026-06-16","cited_by_count":1,"area":"distill"},{"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":"2406.05071","title":"Massively Multiagent Minigames for Training Generalist Agents","created":"2024-06-07","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":"2503.10509","title":"From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL","created":"2025-03-13","cited_by_count":0,"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":"2509.08329","title":"Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2510.22832","title":"HRM-Agent: Training a recurrent reasoning model in dynamic environments using reinforcement learning","created":"2025-10-26","cited_by_count":0,"area":"lr"},{"id":"2602.04868","title":"CRoSS: A Continual Robotic Simulation Suite for Scalable Reinforcement Learning with High Task Diversity and Realistic Physics Simulation","created":"2026-02-04","cited_by_count":0,"area":"deeprl"},{"id":"2604.15044","title":"CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.22454","title":"Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning","created":"2026-05-21","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":"2609.31076","title":"Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.34214","title":"GlyphBench: A Playground for Language-Model Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.19955","title":"Neurosymbolic Learning of Interpretable World Models","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}