91 citations · 115 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2018
Zero-Shot Visual Imitation
Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo +7
The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both 'what' and 'how' to imitate. We pursue an alternative paradigm whe…
cs.LG2016★ 91 cited
Loss is its own Reward: Self-Supervision for Reinforcement Learning
Evan Shelhamer, Parsa Mahmoudieh, Max Argus +1
Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and…