Deep generative models for offline policy learning: Tutorial, survey, and perspectives on future directions
Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …
particularly in generating texts, images, and videos using models trained from offline data …
Hierarchical Multi-contact Motion Planning of Hexapod Robots with Incremental Reinforcement Learning
Legged locomotion in unstructured environments with static and dynamic obstacles is
challenging. This paper proposes a novel Hierarchical Multi-Contact motion planning …
challenging. This paper proposes a novel Hierarchical Multi-Contact motion planning …
EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer
H Dong, H Fu, W Xu, Z Zhou, C Chen - The Thirty-eighth Annual … - openreview.net
Reinforcement Learning (RL) controllers have demonstrated remarkable performance in
complex robot control tasks. However, the presence of reality gap often leads to poor …
complex robot control tasks. However, the presence of reality gap often leads to poor …