Model-Based Reinforcement Learning with State Abstraction: A Survey.
Rolf A. N. StarreMarco LoogFrans A. OliehoekPublished in: BNAIC/BENELEARN (2022)
Keyphrases
- model based reinforcement learning
- state abstraction
- markov decision processes
- reinforcement learning
- state space
- reinforcement learning algorithms
- finite state
- optimal policy
- dynamic programming
- infinite horizon
- policy iteration
- learning algorithm
- partially observable
- markov chain
- decision processes
- markov decision problems
- function approximation
- heuristic search
- average cost
- multi agent
- machine learning