Representations for Stable Off-Policy Reinforcement Learning.
Dibya GhoshMarc G. BellemarePublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- robotic control
- function approximators
- state space
- machine learning
- symbolic representation
- learning algorithm
- optimal policy
- optimal control
- learning agents
- higher level
- active learning
- evolutionary algorithm
- artificial intelligence
- representation scheme
- reinforcement learning algorithms
- real world