Should I Run Offline Reinforcement Learning or Behavioral Cloning?
Aviral KumarJoey HongAnikait SinghSergey LevinePublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- real time
- function approximation
- state space
- reinforcement learning algorithms
- learning algorithm
- action selection
- model free
- continuous state
- reinforcement learning methods
- optimal policy
- markov decision processes
- learning problems
- optimal control
- transition model
- temporal difference
- dynamic programming
- learning process
- artificial intelligence
- information retrieval
- machine learning
- data mining
- data sets