Lyapunov-Constrained Action Sets for Reinforcement Learning.
Theodore J. PerkinsAndrew G. BartoPublished in: ICML (2001)
Keyphrases
- action sets
- reinforcement learning
- adaptive control
- markov decision processes
- function approximation
- state space
- temporal difference
- dynamical systems
- optimal policy
- learning algorithm
- dynamic programming
- finite state
- closed loop
- reinforcement learning algorithms
- sufficient conditions
- multi agent
- model free
- fixed point
- random walk
- supervised learning
- markov decision process
- policy iteration
- markov decision problems
- search algorithm