One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL.

Saurabh Kumar Aviral Kumar Sergey Levine Chelsea Finn

Published in: NeurIPS (2020)

Keyphrases

maximum entropy
video sequences
video data
multi agent
key frames
learning algorithm
reinforcement learning
optimal solution
multi objective
model free
linear equations
video indexing
control policy