Offline RL Policies Should Be Trained to be Adaptive.

Dibya Ghosh Anurag Ajay Pulkit Agrawal Sergey Levine

Published in: ICML (2022)

Keyphrases

optimal policy
reinforcement learning
real time
training set
adaptive control
data sets
neural network
learning algorithm
training data
multi agent
learning classifier systems
control policy
hierarchical reinforcement learning