{"total":20,"rows":[{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"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":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2207.09405","title":"Bayesian Generational Population-Based Training","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2206.04115","title":"Simplifying Polylogarithms with Machine Learning","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2209.10081","title":"Revisiting Discrete Soft Actor-Critic","created":"2022-09-21","cited_by_count":13,"area":null},{"id":"2210.06041","title":"Reinforcement Learning with Automated Auxiliary Loss Search","created":"2022-10-12","cited_by_count":13,"area":null},{"id":"2309.14597","title":"Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control","created":"2023-09-26","cited_by_count":11,"area":null},{"id":"2205.07015","title":"Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments","created":"2022-05-14","cited_by_count":9,"area":null},{"id":"2105.00990","title":"Hierarchical Reinforcement Learning for Air Combat at DARPA's AlphaDogfight Trials","created":"2021-05-03","cited_by_count":8,"area":null},{"id":"2206.08888","title":"Fast Population-Based Reinforcement Learning on a Single Machine","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2212.14538","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","created":"2022-12-30","cited_by_count":6,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2507.11486","title":"Exploring the robustness of TractOracle methods in RL-based tractography","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2410.01643","title":"Stable Offline Value Function Learning with Bisimulation-based Representations","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2602.04166","title":"Topology-Aware Revival for Efficient Sparse Training","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2610.20203","title":"Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving based on Bird's-Eye View in Simulated Cities","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}