{"total":29,"rows":[{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2305.05239","title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","created":"2023-05-09","cited_by_count":14,"area":null},{"id":"2112.04145","title":"A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions","created":"2021-12-08","cited_by_count":12,"area":null},{"id":"2112.09025","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","created":"2021-12-16","cited_by_count":12,"area":null},{"id":"2206.03192","title":"Generalized Data Distribution Iteration","created":"2022-06-07","cited_by_count":12,"area":null},{"id":"2206.05060","title":"Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS","created":"2022-06-10","cited_by_count":10,"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":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2106.00707","title":"An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2106.06232","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2201.06126","title":"Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networks","created":"2022-01-16","cited_by_count":6,"area":null},{"id":"2109.14727","title":"Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2105.07960","title":"Behavior-based Neuroevolutionary Training in Reinforcement Learning","created":"2021-05-17","cited_by_count":3,"area":null},{"id":"2208.00755","title":"Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2110.02421","title":"Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2207.13453","title":"Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2105.03923","title":"CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration","created":"2021-05-09","cited_by_count":1,"area":null},{"id":"2210.12693","title":"Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation","created":"2022-10-23","cited_by_count":1,"area":null},{"id":"2212.05237","title":"Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees","created":"2022-12-10","cited_by_count":1,"area":null},{"id":"2109.11788","title":"Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients","created":"2021-09-24","cited_by_count":0,"area":null},{"id":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null}],"next_cursor":null}