{"total":53,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"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":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"area":null},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136,"area":"wm"},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111,"area":"ssm"},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2312.09187","title":"Vision-Language Models as a Source of Rewards","created":"2023-12-14","cited_by_count":66,"area":"mllm"},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2206.12542","title":"Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning","created":"2022-06-25","cited_by_count":15,"area":null},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2310.11305","title":"MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games","created":"2023-10-17","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":"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":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2409.17652","title":"FactorSim: Generative Simulation via Factorized Representation","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2210.05980","title":"Efficient Offline Policy Optimization with a Learned Model","created":"2022-10-12","cited_by_count":8,"area":"offlinerl"},{"id":"2310.13396","title":"RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup","created":"2023-10-20","cited_by_count":8,"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":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","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":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2107.05405","title":"Learning Expected Emphatic Traces for Deep RL","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2406.06309","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","created":"2024-06-10","cited_by_count":4,"area":"offlinerl"},{"id":"2509.25582","title":"Safe In-Context Reinforcement Learning","created":"2025-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2110.08307","title":"GrowSpace: Learning How to Shape Plants","created":"2021-10-15","cited_by_count":2,"area":null},{"id":"2206.10027","title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","created":"2022-06-20","cited_by_count":2,"area":null},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2409.07606","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","created":"2024-09-11","cited_by_count":2,"area":"offlinerl"},{"id":"2502.16634","title":"OptionZero: Planning with Learned Options","created":"2025-02-23","cited_by_count":2,"area":"deeprl"},{"id":"2106.14080","title":"Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2205.15824","title":"Graph Backup: Data Efficient Backup Exploiting Markovian Transitions","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2301.08442","title":"Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning","created":"2023-01-20","cited_by_count":1,"area":null},{"id":"2302.07985","title":"Trust-Region-Free Policy Optimization for Stochastic Policies","created":"2023-02-15","cited_by_count":1,"area":null},{"id":"2310.20380","title":"Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2302.14451","title":"Hierarchical Reinforcement Learning in Complex 3D Environments","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2308.12649","title":"APART: Diverse Skill Discovery using All Pairs with Ascending Reward and DropouT","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2602.19837","title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.07769","title":"Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms","created":"2026-07-08","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}