{"total":17,"rows":[{"id":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44,"area":null},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"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":"2209.08898","title":"Batch Layer Normalization, A new normalization layer for CNNs and RNN","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2506.06361","title":"Tactile MNIST: Benchmarking Active Tactile Perception","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2506.22174","title":"ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Research","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2502.02382","title":"Circular Microalgae-Based Carbon Control for Net Zero","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2506.18627","title":"Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits","created":"2025-06-23","cited_by_count":1,"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":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2512.12230","title":"Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2104.07361","title":"Scale Invariant Monte Carlo under Linear Function Approximation with Curvature based step-size","created":"2021-04-15","cited_by_count":0,"area":null},{"id":"2608.16607","title":"Interactive Whole Slide Images for RL-based Tumour Segmentation","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2610.01882","title":"Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}