Papers Gym halfcheetah-medium-replay
“Gym halfcheetah-medium-replay” 태그가 달린 논문 2편 · 필터 해제
Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
2024-05-27
· Haoxin Lin, Yu-Yan Xu, Yihao Sun, Zhilong Zhang 외
Model-based methods in reinforcement learning offer a promising approach to enhance data efficiency by facilitating policy exploration within a dynamics model. However, accurately predicting sequential steps in the dynam…
Gym halfcheetah-mediumGym halfcheetah-medium-expertGym halfcheetah-medium-replayGym halfcheetah-random+4Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble
2021-10-04 · NeurIPS 2021 12
· Gaon An, Seungyong Moon, Jang-Hyun Kim, Hyun Oh Song
Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approximation errors from out-of-distribution (…
Adroid door-clonedAdroid door-humanAdroid hammer-clonedAdroid hammer-human+17
1–2 / 2