Convergent reinforcement learning control with neural networks and continuous action search.
Minwoo LeeCharles W. AndersonPublished in: ADPRL (2014)
Keyphrases
- neural network
- reinforcement learning
- continuous state
- continuous action
- policy search
- control problems
- control system
- search algorithm
- search space
- control policy
- control policies
- robot control
- optimal policy
- optimal control
- model free
- reinforcement learning algorithms
- state space
- function approximation
- robot navigation
- control strategies
- action space