| CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels | Feb 19, 2021 | MuJoCo | —Unverified | 0 |
| Q-Value Weighted Regression: Reinforcement Learning with Limited Data | Feb 12, 2021 | Atari Gamescontinuous-control | CodeCode Available | 0 |
| Robust Policy Gradient against Strong Data Corruption | Feb 11, 2021 | continuous-controlContinuous Control | CodeCode Available | 0 |
| Variance Penalized On-Policy and Off-Policy Actor-Critic | Feb 3, 2021 | MuJoCo | CodeCode Available | 0 |
| GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning | Jan 24, 2021 | Decision MakingDeep Reinforcement Learning | —Unverified | 0 |
| Hellinger Distance Constrained Regression | Jan 1, 2021 | MuJoCoregression | —Unverified | 0 |
| Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets | Jan 1, 2021 | D4RLMuJoCo | —Unverified | 0 |
| Self-Supervised Continuous Control without Policy Gradient | Jan 1, 2021 | continuous-controlContinuous Control | —Unverified | 0 |
| MQES: Max-Q Entropy Search for Efficient Exploration in Continuous Reinforcement Learning | Jan 1, 2021 | Efficient ExplorationMuJoCo | —Unverified | 0 |
| Formal Language Constrained Markov Decision Processes | Jan 1, 2021 | MuJoCo | —Unverified | 0 |
