6 citations · 6 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Contrastive World Models
Bonnie Li
World models trained via pixel reconstruction can struggle in visually complex environments, where irrelevant information dominates the objective and distract the model from inform…
cs.LG2021★ 6 cited
Domain Adversarial Reinforcement Learning
Bonnie Li, Vincent François-Lavet, Thang Doan +1
We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ, e.g. when there are different backgrounds or change in co…