{"total":135,"rows":[{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"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":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","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":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42,"area":null},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"area":"agents"},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39,"area":null},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","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":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","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":"2306.03186","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2102.04399","title":"How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation","created":"2021-02-08","cited_by_count":27,"area":null},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2307.07871","title":"The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents","created":"2023-07-15","cited_by_count":24,"area":"agents"},{"id":"2206.09674","title":"EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL","created":"2022-06-20","cited_by_count":23,"area":null},{"id":"2104.07495","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22,"area":"deeprl"},{"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":"2203.04297","title":"R\\'enyi State Entropy for Exploration Acceleration in Reinforcement Learning","created":"2022-03-08","cited_by_count":18,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2506.01538","title":"LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation","created":"2025-06-02","cited_by_count":13,"area":"agents"},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"id":"2301.10886","title":"Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning","created":"2023-01-26","cited_by_count":12,"area":null},{"id":"2402.07411","title":"Potential-Based Reward Shaping For Intrinsic Motivation","created":"2024-02-12","cited_by_count":12,"area":"deeprl"},{"id":"2210.05409","title":"LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2211.00247","title":"Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2510.10959","title":"Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning","created":"2025-10-13","cited_by_count":11,"area":"lr"},{"id":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2306.07290","title":"Value function estimation using conditional diffusion models for control","created":"2023-06-09","cited_by_count":10,"area":"diffusion"},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2402.06819","title":"Monitored Markov Decision Processes","created":"2024-02-09","cited_by_count":10,"area":"deeprl"},{"id":"2405.19548","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","created":"2024-05-29","cited_by_count":10,"area":"deeprl"},{"id":"2410.23022","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","created":"2024-10-30","cited_by_count":10,"area":"agents"},{"id":"2109.08521","title":"Focus on Impact: Indoor Exploration with Intrinsic Motivation","created":"2021-09-14","cited_by_count":9,"area":null},{"id":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9,"area":"offlinerl"},{"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":"2210.00066","title":"Improving Policy Learning via Language Dynamics Distillation","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2211.04878","title":"Foundation Models for Semantic Novelty in Reinforcement Learning","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2607.22724","title":"Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-07-22","cited_by_count":9,"area":"agents"},{"id":"2205.11184","title":"An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"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":"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":"2204.03140","title":"Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2206.11396","title":"Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2209.08842","title":"Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning","created":"2022-09-19","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":"2310.18144","title":"Improving Intrinsic Exploration by Creating Stationary Objectives","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2104.00442","title":"Touch-based Curiosity for Sparse-Reward Tasks","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2201.08300","title":"From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks","created":"2022-01-20","cited_by_count":6,"area":null},{"id":"2301.07150","title":"Embodied Agents for Efficient Exploration and Smart Scene Description","created":"2023-01-17","cited_by_count":6,"area":null},{"id":"2306.09509","title":"Granger Causal Interaction Skill Chains","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2402.02097","title":"Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing","created":"2024-02-03","cited_by_count":6,"area":null},{"id":"2406.13909","title":"Beyond Optimism: Exploration With Partially Observable Rewards","created":"2024-06-20","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2202.08266","title":"Open-Ended Reinforcement Learning with Neural Reward Functions","created":"2022-02-16","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":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2110.06912","title":"OPEn: An Open-ended Physics Environment for Learning Without a Task","created":"2021-10-13","cited_by_count":4,"area":null},{"id":"2307.02889","title":"Learning to Solve Tasks with Exploring Prior Behaviours","created":"2023-07-06","cited_by_count":4,"area":null},{"id":"2505.20726","title":"ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making","created":"2025-05-27","cited_by_count":4,"area":"agents"},{"id":"2211.16838","title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation","created":"2022-11-30","cited_by_count":3,"area":"offlinerl"},{"id":"2308.13661","title":"Go Beyond Imagination: Maximizing Episodic Reachability with World Models","created":"2023-08-25","cited_by_count":3,"area":"wm"},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2402.03138","title":"Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations","created":"2024-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2404.02235","title":"Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning","created":"2024-04-02","cited_by_count":3,"area":"deeprl"},{"id":"2410.12197","title":"Potential-Based Intrinsic Motivation: Preserving Optimality With Complex, Non-Markovian Shaping Rewards","created":"2024-10-16","cited_by_count":3,"area":"deeprl"},{"id":"2107.08888","title":"Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning","created":"2021-07-19","cited_by_count":2,"area":null},{"id":"2203.02298","title":"Intrinsically-Motivated Reinforcement Learning: A Brief Introduction","created":"2022-03-03","cited_by_count":2,"area":null},{"id":"2210.16468","title":"Curiosity-Driven Multi-Agent Exploration with Mixed Objectives","created":"2022-10-29","cited_by_count":2,"area":null},{"id":"2302.04693","title":"Scaling Goal-based Exploration via Pruning Proto-goals","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2310.17537","title":"Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity","created":"2023-10-26","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":"2312.16456","title":"Adaptive trajectory-constrained exploration strategy for deep reinforcement learning","created":"2023-12-27","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":"2503.05573","title":"InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model","created":"2025-03-07","cited_by_count":2,"area":"wm"},{"id":"2508.05182","title":"SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2509.25438","title":"Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring","created":"2025-09-29","cited_by_count":2,"area":"deeprl"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2205.09448","title":"Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes","created":"2022-05-19","cited_by_count":1,"area":null}],"next_cursor":"100"}