DERAIL: Diagnostic Environments for Reward And Imitation Learning.

Pedro Freire Adam Gleave Sam Toyer Stuart Russell

Published in: CoRR (2020)

Keyphrases

imitation learning
reinforcement learning
robotic systems
maximum margin
expert systems
dynamic environments
model free
reinforcement learning methods
dynamic programming
function approximation
humanoid robot
video sequences
mobile robot
state space
action selection
reinforcement learning algorithms