Reinforcement Learning in RDPs by Combining Deep RL with Automata Learning.
Tal ShaharRonen I. BrafmanPublished in: ECAI (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- rl algorithms
- function approximation
- eligibility traces
- reinforcement learning methods
- autonomous learning
- supervised learning
- temporal difference learning
- learning problems
- temporal difference
- learned knowledge
- reinforcement learning algorithms
- model free
- multi agent
- state space
- learning mechanism
- learning capabilities
- actor critic
- transfer learning
- active learning
- optimal policy
- direct policy search
- partially observable domains
- state abstraction
- continuous state
- unsupervised learning
- learning classifier systems
- learning agents
- learning automata
- complex domains
- learning tasks
- regular expressions
- action selection