{"total":11,"rows":[{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"id":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","cited_by_count":13,"area":null},{"id":"2306.11918","title":"Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback","created":"2023-06-20","cited_by_count":9,"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":"2409.08570","title":"Batch Ensemble for Variance Dependent Regret in Stochastic Bandits","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2304.09547","title":"Graph Exploration for Effective Multi-agent Q-Learning","created":"2023-04-19","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":"2210.05262","title":"Factors of Influence of the Overestimation Bias of Q-Learning","created":"2022-10-11","cited_by_count":0,"area":null}],"next_cursor":null}