[Paper][RL] [ToDo]Mutual Information State Intrinsic Control 리뷰

https://arxiv.org/abs/2103.08107#:~:text=Reinforcement%20learning%20has%20been%20shown,defining%20an%20intrinsic%20reward%20function. Mutual Information State Intrinsic Control Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts to remove this constraint by defining an..

2022.05.19