Overfitting-avoiding goal-guided exploration for hard-exploration multi-goal reinforcement learning

Han, Changlin; Peng, Zhiyong; Liu, Yadong; Tang, Jingsheng; Yu, Yang; Zhou, Zongtan

doi:10.1016/j.neucom.2023.01.016

Cited by 5 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hindsight Experience Replay (HER) has paved a promising path toward increasing the efficiency of goal-conditioned tasks with sparse rewards 6 . Several variants have been proposed to enhance HER, such as curriculum learning to maximize the diversity of the achieved goals 36 , providing demonstrations 37 , generating more valuable desired goals 38 , and curiosity-driven exploration 39 . Legged locomotion tasks can be viewed as a particular variant of goalconditioned tasks due to the presence of control commands.…”

Section: Related Workmentioning

confidence: 99%

Learning Agility and Adaptive Legged Locomotion via Curricular Hindsight Reinforcement Learning

Li,

Pang,

Bai

et al. 2024

Preprint

View full text Add to dashboard Cite

Agile and adaptive maneuvers such as fall recovery, high-speed turning, and sprinting in the wild are challenging for legged systems. We propose a Curricular Hindsight Reinforcement Learning (CHRL) that learns an end-to-end tracking controller that achieves powerful agility and adaptation for the legged robot. The two key components are (i) a novel automatic curriculum strategy on task difficulty and (ii) a Hindsight Experience Replay strategy adapted to legged locomotion tasks. We demonstrated successful agile and adaptive locomotion on a real quadruped robot that performed fall recovery autonomously, coherent trotting, sustained outdoor running speeds up to 3.45 m/s, and tuning speeds up to 3.2 rad/s. This system produces adaptive behaviors responding to changing situations and unexpected disturbances on natural terrains like grass and dirt.

show abstract