SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards.
Siddharth ReddyAnca D. DraganSergey LevinePublished in: ICLR (2020)
Keyphrases
- reinforcement learning
- imitation learning
- reinforcement learning methods
- function approximation
- state space
- optimal policy
- markov decision processes
- model free
- reinforcement learning algorithms
- high dimensional
- machine learning
- temporal difference
- multi agent
- action selection
- reward function
- control problems
- learning algorithm
- supervised learning
- learning problems
- maximum likelihood
- image sequences