{"total":15,"rows":[{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2206.03787","title":"Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance","created":"2022-06-08","cited_by_count":22,"area":null},{"id":"2305.17109","title":"Reinforcement Learning with Simple Sequence Priors","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2202.03957","title":"Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2401.00015","title":"Distributional Reinforcement Learning-based Energy Arbitrage Strategies in Imbalance Settlement Mechanism","created":"2023-12-23","cited_by_count":5,"area":null},{"id":"2406.04144","title":"Redundancy-aware Action Spaces for Robot Learning","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2201.01369","title":"Using Simulation Optimization to Improve Zero-shot Policy Transfer of Quadrotors","created":"2022-01-04","cited_by_count":4,"area":null},{"id":"2303.15178","title":"Robust Path Following on Rivers Using Bootstrapped Reinforcement Learning","created":"2023-03-24","cited_by_count":3,"area":null},{"id":"2202.13638","title":"GPU-Accelerated Policy Optimization via Batch Automatic Differentiation of Gaussian Processes for Real-World Control","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2208.00003","title":"RangL: A Reinforcement Learning Competition Platform","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2209.07758","title":"Game-theoretic Objective Space Planning","created":"2022-09-16","cited_by_count":0,"area":null},{"id":"2607.25190","title":"Lloyd's $K$-Means Clustering Algorithm Is Frank-Wolfe in Disguise","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.24488","title":"Where Entropy Is Measured Matters: Policy Geometry in Bounded Continuous-Control PPO","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.23269","title":"Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":null}