{"total":125,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184,"area":null},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"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":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72,"area":null},{"id":"2306.01711","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","created":"2023-06-02","cited_by_count":70,"area":null},{"id":"2110.01219","title":"Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation","created":"2021-10-04","cited_by_count":68,"area":null},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37,"area":null},{"id":"2303.16563","title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","created":"2023-03-29","cited_by_count":36,"area":null},{"id":"2106.14876","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","created":"2021-06-28","cited_by_count":35,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2405.15143","title":"Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models","created":"2024-05-24","cited_by_count":33,"area":null},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2102.12463","title":"Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2301.02099","title":"Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping","created":"2023-01-05","cited_by_count":25,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2108.05533","title":"Efficient Local Planning with Linear Function Approximation","created":"2021-08-12","cited_by_count":23,"area":null},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23,"area":null},{"id":"2108.11811","title":"When should agents explore?","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2203.04297","title":"R\\'enyi State Entropy for Exploration Acceleration in Reinforcement Learning","created":"2022-03-08","cited_by_count":18,"area":null},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15,"area":null},{"id":"2102.03140","title":"Sparse Reward Exploration via Novelty Search and Emitters","created":"2021-02-05","cited_by_count":13,"area":null},{"id":"2112.04145","title":"A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions","created":"2021-12-08","cited_by_count":12,"area":null},{"id":"2206.03192","title":"Generalized Data Distribution Iteration","created":"2022-06-07","cited_by_count":12,"area":null},{"id":"2412.10675","title":"Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation","created":"2024-12-14","cited_by_count":11,"area":null},{"id":"2102.11051","title":"Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2210.12806","title":"Active Exploration for Robotic Manipulation","created":"2022-10-23","cited_by_count":10,"area":null},{"id":"2301.12579","title":"Sample Efficient Deep Reinforcement Learning via Local Planning","created":"2023-01-29","cited_by_count":10,"area":null},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2104.11707","title":"DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies","created":"2021-04-23","cited_by_count":9,"area":null},{"id":"2110.00898","title":"A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances","created":"2021-10-03","cited_by_count":9,"area":null},{"id":"2206.05497","title":"Mutation Models: Learning to Generate Levels by Imitating Evolution","created":"2022-06-11","cited_by_count":9,"area":null},{"id":"2207.05742","title":"Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning","created":"2022-07-12","cited_by_count":9,"area":null},{"id":"2304.13424","title":"Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories","created":"2023-04-26","cited_by_count":9,"area":null},{"id":"2310.19424","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2105.04607","title":"Efficient Self-Supervised Data Collection for Offline Robot Learning","created":"2021-05-10","cited_by_count":8,"area":null},{"id":"2310.20178","title":"Learning to Discover Skills through Guidance","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2412.06438","title":"Can foundation models actively gather information in interactive environments to test hypotheses?","created":"2024-12-09","cited_by_count":8,"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":"2106.06232","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2304.00046","title":"Accelerating exploration and representation learning with offline pre-training","created":"2023-03-31","cited_by_count":7,"area":null},{"id":"2101.06177","title":"Hierarchical Width-Based Planning and Learning","created":"2021-01-15","cited_by_count":6,"area":null},{"id":"2109.13388","title":"Go-Blend behavior and affect","created":"2021-09-24","cited_by_count":6,"area":null},{"id":"2211.04786","title":"Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2509.19292","title":"SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2111.01919","title":"Discovering and Exploiting Sparse Rewards in a Learned Behavior Space","created":"2021-11-02","cited_by_count":5,"area":null},{"id":"2208.14928","title":"Cell-Free Latent Go-Explore","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2402.17978","title":"Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning","created":"2024-02-28","cited_by_count":5,"area":null},{"id":"2505.15251","title":"Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"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":"2103.06370","title":"Causal-aware Safe Policy Improvement for Task-oriented dialogue","created":"2021-03-10","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":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2107.05786","title":"Carle's Game: An Open-Ended Challenge in Exploratory Machine Creativity","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2110.14615","title":"Play to Grade: Testing Coding Games as Classifying Markov Decision Process","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2202.05129","title":"Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2203.01004","title":"Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2209.00570","title":"Go-Explore Complex 3D Game Environments for Automated Reachability Testing","created":"2022-09-01","cited_by_count":3,"area":null},{"id":"2210.11442","title":"Augmentative Topology Agents For Open-Ended Learning","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2210.16058","title":"Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learning","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2301.13758","title":"Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environments","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2305.10267","title":"State Representation Learning Using an Unbalanced Atlas","created":"2023-05-17","cited_by_count":3,"area":null},{"id":"2410.04855","title":"Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2607.22832","title":"MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution","created":"2026-07-24","cited_by_count":3,"area":null},{"id":"2107.06405","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","created":"2021-07-13","cited_by_count":2,"area":null},{"id":"2107.08888","title":"Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning","created":"2021-07-19","cited_by_count":2,"area":null},{"id":"2109.10173","title":"Long-Term Exploration in Persistent MDPs","created":"2021-09-21","cited_by_count":2,"area":null},{"id":"2303.04327","title":"Using Memory-Based Learning to Solve Tasks with State-Action Constraints","created":"2023-03-08","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":"2406.10127","title":"Exploration by Learning Diverse Skills through Successor State Measures","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2104.04768","title":"Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms","created":"2021-04-10","cited_by_count":1,"area":null},{"id":"2105.02580","title":"Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2112.08736","title":"Learning to Minimize Cost-to-Serve for Multi-Node Multi-Product Order Fulfilment in Electronic Commerce","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2203.00874","title":"Follow your Nose: Using General Value Functions for Directed Exploration in Reinforcement Learning","created":"2022-03-02","cited_by_count":1,"area":null},{"id":"2301.05635","title":"Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm","created":"2023-01-13","cited_by_count":1,"area":null},{"id":"2308.09909","title":"Never Explore Repeatedly in Multi-Agent Reinforcement Learning","created":"2023-08-19","cited_by_count":1,"area":null},{"id":"2311.15089","title":"Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning","created":"2023-11-25","cited_by_count":1,"area":null},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2410.11155","title":"Latent-Predictive Empowerment: Measuring Empowerment without a Simulator","created":"2024-10-15","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}],"next_cursor":"100"}