Login / Signup

GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation.

Abhinav JainVaibhav V. Unhelkar
Published in: CoRR (2023)
Keyphrases
  • stationary distribution
  • imitation learning
  • markov chain
  • random walk
  • queueing networks
  • initial state
  • transition probabilities
  • queue length
  • parameter estimation
  • service times
  • reinforcement learning
  • maximum entropy