Actor-Critic Policy Learning in Cooperative Planning.
Josh ReddingAlborz GeramifardJonathan P. HowPublished in: AAAI Spring Symposium: Embedded Reasoning (2010)
Keyphrases
- actor critic
- policy gradient
- reinforcement learning
- cooperative
- learning algorithm
- policy gradient methods
- learning tasks
- partially observable
- approximate dynamic programming
- function approximation
- temporal difference
- active learning
- action selection
- markov decision processes
- optimal control
- finite state
- dynamical systems
- supervised learning