Initial State Interventions for Deconfounded Imitation Learning.

Samuel Pfrommer Yatong Bai Hyunin Lee Somayeh Sojoudi

Published in: CDC (2023)

Keyphrases

initial state
imitation learning
reinforcement learning
state space
optimal policy
situation calculus
robotic systems
humanoid robot
maximum margin
probability distribution
multi modal
relational databases
knowledge representation
decision problems
average cost
markov decision process