Continuous-Action Q-Learning.
José del R. MillánDaniele PosenatoEric DedieuPublished in: Mach. Learn. (2002)
Keyphrases
- continuous action
- continuous state and action spaces
- policy search
- reinforcement learning
- reinforcement learning algorithms
- continuous state
- action space
- state space
- function approximation
- multi agent
- partially observable markov decision processes
- cooperative
- model free
- state action
- markov decision processes
- optimal policy
- action selection
- reward function
- learning algorithm
- learning rate
- machine learning
- function approximators
- dynamic programming
- temporal difference
- evaluation function
- stochastic games
- heuristic search