Skew-Fit: State-Covering Self-Supervised Reinforcement Learning.

Vitchyr Pong Murtaza Dalal Steven Lin Ashvin Nair Shikhar Bahl Sergey Levine

Published in: ICML (2020)

Keyphrases

reinforcement learning
state space
neural network
function approximation
state abstraction
machine learning
case study
multi agent
expert systems
optimal policy
markov decision processes
partially observable