{"total":37,"rows":[{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"2110.02544","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","created":"2021-10-06","cited_by_count":108,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2111.03941","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","created":"2021-11-06","cited_by_count":23,"area":null},{"id":"2103.06484","title":"Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":22,"area":null},{"id":"2206.08737","title":"N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments","created":"2022-06-17","cited_by_count":16,"area":null},{"id":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2112.06061","title":"OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion","created":"2021-12-11","cited_by_count":10,"area":null},{"id":"2112.11622","title":"An Alternate Policy Gradient Estimator for Softmax Policies","created":"2021-12-22","cited_by_count":9,"area":null},{"id":"2107.01348","title":"Examining average and discounted reward optimality criteria in reinforcement learning","created":"2021-07-03","cited_by_count":6,"area":null},{"id":"2204.06117","title":"AdaTest:Reinforcement Learning and Adaptive Sampling for On-chip Hardware Trojan Detection","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2310.17485","title":"Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2406.01853","title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2308.12772","title":"Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2405.01684","title":"Intelligent Switching for Reset-Free RL","created":"2024-05-02","cited_by_count":4,"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":"2212.04136","title":"Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2301.02593","title":"Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads","created":"2023-01-06","cited_by_count":2,"area":null},{"id":"2304.12330","title":"Parallel bootstrap-based on-policy deep reinforcement learning for continuous flow control applications","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2305.18701","title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2307.08794","title":"Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning","created":"2023-07-17","cited_by_count":2,"area":null},{"id":"2111.06780","title":"AWD3: Dynamic Reduction of the Estimation Bias","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2302.01301","title":"MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2401.09840","title":"FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2211.07434","title":"Parallel Automatic History Matching Algorithm Using Reinforcement Learning","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2211.08272","title":"Low-Thrust Orbital Transfer using Dynamics-Agnostic Reinforcement Learning","created":"2022-10-06","cited_by_count":0,"area":null},{"id":"2305.02882","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2608.14940","title":"When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2610.07562","title":"Learning a Mixture of GFlowNets","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}