13 citations · 14 across the 2 of their papers we have counts for
3 papers
cs.LG2021★ 1 cited
Unsupervised Learning of Visual 3D Keypoints for Control
Boyuan Chen, Pieter Abbeel, Deepak Pathak
Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured laten…
cs.AI2021★ 13 cited
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
Zhenggang Tang, Chao Yu, Boyuan Chen +6
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games. Combining reward randomization a…
cs.LG2019
Zero-shot Policy Learning with Spatial Temporal RewardDecomposition on Contingency-aware Observation
Huazhe Xu, Boyuan Chen, Yang Gao +1
It is a long-standing challenge to enable an intelligent agent to learn in one environment and generalize to an unseen environment without further data collection and finetuning. I…