Imitation Bootstrapped Reinforcement Learning.
Hengyuan HuSuvir MirchandaniDorsa SadighPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- machine learning
- state space
- multi agent
- temporal difference learning
- model free
- optimal policy
- temporal difference
- control problems
- supervised learning
- learning process
- action selection
- learning capabilities
- markov decision processes
- learning problems
- reinforcement learning methods
- action space
- robotic control
- imitation learning
- decision trees
- partially observable
- support vector
- learning classifier systems
- information systems