31 citations · 67 across the 8 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 31 cited
Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations
Daniel S. Brown, Wonjoon Goo, Scott Niekum
The performance of imitation learning is typically upper-bounded by the performance of the demonstrator. While recent empirical results demonstrate that ranked demonstrations allow…
cs.LG2019★ 30 cited
Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
Daniel S. Brown, Wonjoon Goo, Prabhat Nagarajan +1
A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a rewa…