{"total":169,"rows":[{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"area":null},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2103.16089","title":"Reinforcement learning for optimization of variational quantum circuit architectures","created":"2021-03-30","cited_by_count":77,"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":"2106.03894","title":"Differentiable Quality Diversity","created":"2021-06-07","cited_by_count":72,"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":"2204.05080","title":"Semantic Exploration from Language Abstractions and Pretrained Representations","created":"2022-04-08","cited_by_count":51,"area":null},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2211.12870","title":"ActMAD: Activation Matching to Align Distributions for Test-Time-Training","created":"2022-11-23","cited_by_count":41,"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":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"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":"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":"2106.05648","title":"Unsupervised Behaviour Discovery with Quality-Diversity Optimisation","created":"2021-06-10","cited_by_count":30,"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":"2206.00484","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","created":"2022-05-30","cited_by_count":29,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","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":"2303.13002","title":"Planning Goals for Exploration","created":"2023-03-23","cited_by_count":28,"area":null},{"id":"2306.03186","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24,"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":"2201.01251","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games","created":"2022-01-04","cited_by_count":22,"area":null},{"id":"2305.20065","title":"Latent Exploration for Reinforcement Learning","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2505.11581","title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","created":"2025-05-16","cited_by_count":22,"area":null},{"id":"2212.02779","title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","created":"2022-12-06","cited_by_count":21,"area":null},{"id":"2109.08522","title":"Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires","created":"2021-09-16","cited_by_count":20,"area":null},{"id":"2205.14345","title":"Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2302.07515","title":"TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play","created":"2023-02-15","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":"2206.13477","title":"Parametrically Retargetable Decision-Makers Tend To Seek Power","created":"2022-06-27","cited_by_count":19,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2303.04077","title":"Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding","created":"2023-03-07","cited_by_count":18,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"area":null},{"id":"2512.01061","title":"Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer","created":"2025-11-30","cited_by_count":15,"area":null},{"id":"2202.01258","title":"Accelerated Quality-Diversity through Massive Parallelism","created":"2022-02-02","cited_by_count":14,"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":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2210.05409","title":"LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2309.14104","title":"Affective Game Computing: A Survey","created":"2023-09-25","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2111.00213","title":"Adjacency constraint for efficient hierarchical reinforcement learning","created":"2021-10-30","cited_by_count":10,"area":null},{"id":"2206.05060","title":"Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS","created":"2022-06-10","cited_by_count":10,"area":null},{"id":"2210.02622","title":"Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing","created":"2022-10-06","cited_by_count":10,"area":null},{"id":"2211.02193","title":"Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning","created":"2022-11-04","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":"2312.11522","title":"Assessing SATNet's Ability to Solve the Symbol Grounding Problem","created":"2023-12-13","cited_by_count":10,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2309.09752","title":"Contrastive Initial State Buffer for Reinforcement Learning","created":"2023-09-18","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":"2105.14780","title":"Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning","created":"2021-05-31","cited_by_count":7,"area":null},{"id":"2106.03853","title":"DisTop: Discovering a Topological representation to learn diverse and rewarding skills","created":"2021-06-06","cited_by_count":7,"area":null},{"id":"2203.11369","title":"Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2209.00459","title":"Generative Personas That Behave and Experience Like Humans","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2210.09918","title":"Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity","created":"2022-10-18","cited_by_count":7,"area":null},{"id":"2212.09510","title":"Near-optimal Policy Identification in Active Reinforcement Learning","created":"2022-12-19","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":"2111.01009","title":"Fragment-based Sequential Translation for Molecular Optimization","created":"2021-10-26","cited_by_count":6,"area":null},{"id":"2111.07395","title":"Explicit Explore, Exploit, or Escape ($E^4$): near-optimal safety-constrained reinforcement learning in polynomial time","created":"2021-11-14","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2208.12622","title":"Play with Emotion: Affect-Driven Reinforcement Learning","created":"2022-08-26","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":"2303.06164","title":"Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning","created":"2023-03-10","cited_by_count":6,"area":null},{"id":"2305.08932","title":"MIMEx: Intrinsic Rewards from Masked Input Modeling","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2401.08632","title":"Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning","created":"2023-12-10","cited_by_count":6,"area":null},{"id":"2503.21474","title":"The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Games","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2202.08266","title":"Open-Ended Reinforcement Learning with Neural Reward Functions","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2204.05726","title":"Hierarchical Quality-Diversity for Online Damage Recovery","created":"2022-04-12","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":"2212.04581","title":"PALMER: Perception-Action Loop with Memory for Long-Horizon Planning","created":"2022-12-08","cited_by_count":5,"area":null},{"id":"2306.08641","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","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":"2406.08315","title":"Improving Policy Optimization via $\\varepsilon$-Retrain","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2104.10610","title":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2111.12045","title":"Adaptive Multi-Goal Exploration","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2202.12174","title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2210.05845","title":"Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2303.09032","title":"Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning","created":"2023-03-16","cited_by_count":4,"area":null},{"id":"2401.13460","title":"Multi-Agent Diagnostics for Robustness via Illuminated Diversity","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2410.09187","title":"Automated Rewards via LLM-Generated Progress Functions","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2104.05902","title":"Bi-level Off-policy Reinforcement Learning for Volt/VAR Control Involving Continuous and Discrete Devices","created":"2021-04-13","cited_by_count":3,"area":null},{"id":"2106.05332","title":"Reinforcement Learning for Industrial Control Network Cyber Security Orchestration","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2201.07224","title":"NSGZero: Efficiently Learning Non-Exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search","created":"2022-01-17","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":"2205.13528","title":"SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning","created":"2022-05-26","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":"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":"2302.12359","title":"Targeted Search Control in AlphaZero for Effective Policy Improvement","created":"2023-02-23","cited_by_count":3,"area":null},{"id":"2304.03672","title":"Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains","created":"2023-04-07","cited_by_count":3,"area":null},{"id":"2304.07425","title":"Efficient Quality-Diversity Optimization through Diverse Quality Species","created":"2023-04-14","cited_by_count":3,"area":null}],"next_cursor":"100"}