Tree Based Discretization for Continuous State Space Reinforcement Learning.
William T. B. UtherManuela M. VelosoPublished in: AAAI/IAAI (1998)
Keyphrases
- continuous state spaces
- reinforcement learning
- state space
- action space
- control problems
- continuous state
- markov decision processes
- rl algorithms
- model free
- function approximation
- markov decision problems
- optimal control
- learning algorithm
- reinforcement learning algorithms
- heuristic search
- optimal policy
- transfer learning
- dynamic programming
- adaptive control
- search space
- real valued
- learning problems
- control policies