{"total":140,"rows":[{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108,"area":null},{"id":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98,"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":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"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":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49,"area":null},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"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":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2101.02055","title":"Geometric Entropic Exploration","created":"2021-01-06","cited_by_count":32,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"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":"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":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"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":"2209.07550","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":"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":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2105.05347","title":"Return-based Scaling: Yet Another Normalisation Trick for Deep RL","created":"2021-05-11","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":"2201.01251","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games","created":"2022-01-04","cited_by_count":22,"area":null},{"id":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2305.19476","title":"Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2110.10735","title":"Dynamic Bottleneck for Robust Self-Supervised Exploration","created":"2021-10-20","cited_by_count":21,"area":null},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21,"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":"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":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2103.07084","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","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":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","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":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2101.09458","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","created":"2021-01-23","cited_by_count":14,"area":null},{"id":"2202.05195","title":"Uncovering Instabilities in Variational-Quantum Deep Q-Networks","created":"2022-02-10","cited_by_count":14,"area":null},{"id":"2305.05239","title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","created":"2023-05-09","cited_by_count":14,"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":"2301.10886","title":"Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning","created":"2023-01-26","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":"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":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","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":"2102.11329","title":"Action Redundancy in Reinforcement Learning","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","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":"2211.04878","title":"Foundation Models for Semantic Novelty in Reinforcement Learning","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2305.01521","title":"Unlocking the Power of Representations in Long-term Novelty-based Exploration","created":"2023-05-02","cited_by_count":9,"area":null},{"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":"2309.09752","title":"Contrastive Initial State Buffer for Reinforcement Learning","created":"2023-09-18","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":"2106.00707","title":"An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning","created":"2021-06-01","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":"2301.02083","title":"Self-Motivated Multi-Agent Exploration","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2304.10770","title":"DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2310.07745","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2312.12145","title":"OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2402.02468","title":"Fast Peer Adaptation with Context-aware Exploration","created":"2024-02-04","cited_by_count":7,"area":null},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2201.12434","title":"Do You Need the Entropy Reward (in Practice)?","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2308.04836","title":"Beyond Surprise: Improving Exploration Through Surprise Novelty","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2309.02429","title":"Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach","created":"2023-09-05","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":"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":"2205.10484","title":"Nuclear Norm Maximization Based Curiosity-Driven Learning","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2207.12217","title":"Finite-Time Analysis of Asynchronous Q-learning under Diminishing Step-Size from Control-Theoretic View","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2211.10515","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2301.01609","title":"Emergent collective intelligence from massive-agent cooperation and competition","created":"2023-01-04","cited_by_count":4,"area":null},{"id":"2303.12957","title":"Reinforcement Learning with Exogenous States and Rewards","created":"2023-03-22","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":"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":"2104.14138","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2201.06468","title":"Chaining Value Functions for Off-Policy Learning","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2308.09289","title":"Preference-conditioned Pixel-based AI Agent For Game Testing","created":"2023-08-18","cited_by_count":3,"area":null},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2412.20361","title":"Safe Multiagent Coordination via Entropic Exploration","created":"2024-12-29","cited_by_count":3,"area":null},{"id":"2510.09596","title":"BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2106.00266","title":"Did I do that? Blame as a means to identify controlled effects in reinforcement learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2107.01904","title":"Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning","created":"2021-07-05","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":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null}],"next_cursor":"100"}