{"total":87,"rows":[{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2106.05087","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","created":"2021-06-09","cited_by_count":55,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2201.12250","title":"Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2202.13914","title":"Combining Modular Skills in Multitask Learning","created":"2022-02-28","cited_by_count":28,"area":null},{"id":"2508.12511","title":"Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference","created":"2025-08-17","cited_by_count":23,"area":null},{"id":"2112.13941","title":"Safe Reinforcement Learning with Chance-constrained Model Predictive Control","created":"2021-12-27","cited_by_count":20,"area":null},{"id":"2106.03442","title":"Average-Reward Reinforcement Learning with Trust Region Methods","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2108.13680","title":"Learning Practically Feasible Policies for Online 3D Bin Packing","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2201.11817","title":"Modeling Human Exploration Through Resource-Rational Reinforcement Learning","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2212.02094","title":"Learning Physically Realizable Skills for Online Packing of General 3D Shapes","created":"2022-12-05","cited_by_count":12,"area":null},{"id":"2106.04306","title":"Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty","created":"2021-06-08","cited_by_count":10,"area":null},{"id":"2207.01566","title":"General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2311.02104","title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2306.13284","title":"Correcting discount-factor mismatch in on-policy policy gradient methods","created":"2023-06-23","cited_by_count":9,"area":null},{"id":"2510.18460","title":"Learning Boltzmann Generators via Constrained Mass Transport","created":"2025-10-21","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2208.07123","title":"Online 3D Bin Packing Reinforcement Learning Solution with Buffer","created":"2022-08-15","cited_by_count":8,"area":null},{"id":"2302.02477","title":"Offline Learning of Closed-Loop Deep Brain Stimulation Controllers for Parkinson Disease Treatment","created":"2023-02-05","cited_by_count":8,"area":null},{"id":"2509.11481","title":"RAPTOR: A Foundation Policy for Quadrotor Control","created":"2025-09-15","cited_by_count":8,"area":null},{"id":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2102.06737","title":"Kronecker-factored Quasi-Newton Methods for Deep Learning","created":"2021-02-12","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2410.22568","title":"Fast Deep Hedging with Second-Order Optimization","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2112.01853","title":"Episodic Policy Gradient Training","created":"2021-12-03","cited_by_count":5,"area":null},{"id":"2203.16777","title":"Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2305.05812","title":"Assessment of Reinforcement Learning Algorithms for Nuclear Power Plant Fuel Optimization","created":"2023-05-09","cited_by_count":5,"area":null},{"id":"2204.09315","title":"Learning to Constrain Policy Optimization with Virtual Trust Region","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2206.11708","title":"Reinforcement Learning under Partial Observability Guided by Learned Environment Models","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2302.00808","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2305.09041","title":"What Matters in Reinforcement Learning for Tractography","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2312.08103","title":"Machine Learning for the Multi-Dimensional Bin Packing Problem: Literature Review and Empirical Evaluation","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2504.04421","title":"Deliberate Planning of 3D Bin Packing on Packing Configuration Trees","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2105.03172","title":"Reward prediction for representation learning and reward shaping","created":"2021-05-07","cited_by_count":3,"area":null},{"id":"2112.02045","title":"An Analytical Update Rule for General Policy Optimization","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2205.15379","title":"Truly Deterministic Policy Optimization","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2206.03171","title":"Introspective Experience Replay: Look Back When Surprised","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2310.01154","title":"Modularity in Deep Learning: A Survey","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2103.14407","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2104.04424","title":"Behavior-Guided Actor-Critic: Improving Exploration via Learning Policy Behavior Representation for Deep Reinforcement Learning","created":"2021-04-09","cited_by_count":2,"area":null},{"id":"2107.01025","title":"Structure-aware reinforcement learning for node-overload protection in mobile edge computing","created":"2021-06-29","cited_by_count":2,"area":null},{"id":"2107.03759","title":"Analytically Tractable Hidden-States Inference in Bayesian Neural Networks","created":"2021-07-08","cited_by_count":2,"area":null},{"id":"2108.06911","title":"Optimal Actor-Critic Policy with Optimized Training Datasets","created":"2021-08-16","cited_by_count":2,"area":null},{"id":"2108.12581","title":"Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents","created":"2021-08-28","cited_by_count":2,"area":null},{"id":"2112.02095","title":"Intelligent Trading Systems: A Sentiment-Aware Reinforcement Learning Approach","created":"2021-11-14","cited_by_count":2,"area":null},{"id":"2210.11377","title":"Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2304.11593","title":"System III: Learning with Domain Knowledge for Safety Constraints","created":"2023-04-23","cited_by_count":2,"area":null},{"id":"2307.13192","title":"Counterfactual Explanation Policies in RL","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2310.13129","title":"Deep Reinforcement Learning-based Intelligent Traffic Signal Controls with Optimized CO2 emissions","created":"2023-10-19","cited_by_count":2,"area":null},{"id":"2410.03892","title":"Towards Cost Sensitive Decision Making","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2101.06608","title":"Network Automatic Pruning: Start NAP and Take a Nap","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2106.13037","title":"Mix and Mask Actor-Critic Methods","created":"2021-06-24","cited_by_count":1,"area":null},{"id":"2106.14295","title":"A Reinforcement Learning Approach for Sequential Spatial Transformer Networks","created":"2021-06-27","cited_by_count":1,"area":null},{"id":"2107.06686","title":"Safer Reinforcement Learning through Transferable Instinct Networks","created":"2021-07-14","cited_by_count":1,"area":null},{"id":"2110.10017","title":"Neural Network Compatible Off-Policy Natural Actor-Critic Algorithm","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2201.05918","title":"Recursive Least Squares Advantage Actor-Critic Algorithms","created":"2022-01-15","cited_by_count":1,"area":null},{"id":"2201.09104","title":"Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning","created":"2022-01-22","cited_by_count":1,"area":null},{"id":"2204.04718","title":"Rethinking Exponential Averaging of the Fisher","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2207.02074","title":"Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2209.14488","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2212.05572","title":"Off-Policy Deep Reinforcement Learning Algorithms for Handling Various Robotic Manipulator Tasks","created":"2022-12-11","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":"2308.10203","title":"Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL","created":"2023-08-20","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":"2501.01874","title":"DFF: Decision-Focused Fine-tuning for Smarter Predict-then-Optimize with Limited Data","created":"2025-01-03","cited_by_count":1,"area":null},{"id":"2103.06371","title":"Hard Attention Control By Mutual Information Maximization","created":"2021-03-10","cited_by_count":0,"area":null},{"id":"2108.01215","title":"Variational Actor-Critic Algorithms","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2205.02119","title":"Processing Network Controls via Deep Reinforcement Learning","created":"2022-05-01","cited_by_count":0,"area":null},{"id":"2205.15656","title":"Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems","created":"2022-05-31","cited_by_count":0,"area":null},{"id":"2208.09322","title":"Entropy Augmented Reinforcement Learning","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2303.18083","title":"Analysis and Comparison of Two-Level KFAC Methods for Training Deep Neural Networks","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2306.16503","title":"SARC: Soft Actor Retrospective Critic","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2401.01579","title":"An Invariant Information Geometric Method for High-Dimensional Online Optimization","created":"2024-01-03","cited_by_count":0,"area":null},{"id":"2601.10498","title":"PROMA: Projected Microbatch Accumulation for Reference-Free Proximal Policy Updates","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2605.26784","title":"Ratio-Variance Regularized Policy Optimization","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2610.02828","title":"FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}