Demonstration-Regularized RL.
Daniil TiapkinDenis BelomestnyDaniele CalandrielloEric MoulinesAlexey NaumovPierre PerraultMichal ValkoPierre MénardPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- least squares
- information systems
- total least squares
- state space
- autonomous learning
- learning classifier systems
- regularized least squares
- optimal policy
- function approximation
- reinforcement learning algorithms
- learning agents
- optimal control
- exploration exploitation tradeoff
- regularization framework
- genetic algorithm
- multi agent
- learning algorithm