Towards Possibilistic Reinforcement Learning Algorithms.
Régis SabbadinPublished in: FUZZ-IEEE (2001)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- model free
- reinforcement learning problems
- learning algorithm
- temporal difference
- eligibility traces
- reinforcement learning methods
- function approximation
- expected utility
- policy search
- dynamic programming
- partially observable environments
- reward function
- policy gradient
- function approximators
- policy iteration
- markov decision process
- decision theory
- utility function
- dynamic environments
- training data