RLIF: Interactive Imitation Learning as Reinforcement Learning.
Jianlan LuoPerry DongYuexiang ZhaiYi MaSergey LevinePublished in: CoRR (2023)
Keyphrases
- imitation learning
- reinforcement learning
- reinforcement learning methods
- state space
- function approximation
- multi agent
- control problems
- reinforcement learning algorithms
- learning process
- markov decision processes
- machine learning
- model free
- optimal policy
- supervised learning
- learning algorithm
- learning problems
- robotic systems
- action selection
- dynamic programming
- transfer learning
- humanoid robot
- training data
- real time