{"total":13,"rows":[{"id":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43,"area":null},{"id":"2103.06469","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":23,"area":null},{"id":"2103.11883","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","created":"2021-03-22","cited_by_count":19,"area":null},{"id":"2203.01671","title":"Constrained unsupervised anomaly segmentation","created":"2022-03-03","cited_by_count":19,"area":null},{"id":"2205.07983","title":"Test-Time Adaptation with Shape Moments for Image Segmentation","created":"2022-05-16","cited_by_count":19,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2111.02104","title":"Model-Based Episodic Memory Induces Dynamic Hybrid Controls","created":"2021-11-03","cited_by_count":14,"area":null},{"id":"2310.18803","title":"Weakly Coupled Deep Q-Networks","created":"2023-10-28","cited_by_count":6,"area":null},{"id":"2109.00482","title":"Looking at the whole picture: constrained unsupervised anomaly segmentation","created":"2021-09-01","cited_by_count":4,"area":null},{"id":"2109.10736","title":"Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods","created":"2021-09-22","cited_by_count":2,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2211.01266","title":"Knowing the Past to Predict the Future: Reinforcement Virtual Learning","created":"2022-11-02","cited_by_count":0,"area":null}],"next_cursor":null}