Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space.
Zhou FanRui SuWeinan ZhangYong YuPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- action space
- actor critic
- state space
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- policy iteration
- function approximation
- policy gradient
- reinforcement learning methods
- action selection
- multi agent
- control problems
- model free
- state action
- approximate dynamic programming
- real valued
- function approximators
- gradient method
- rl algorithms
- single agent
- learning algorithm
- supervised learning
- optimal control
- partially observable markov decision processes
- average reward
- machine learning
- markov decision problems
- optimal policy
- markov decision process
- partially observable
- learning problems
- multi agent systems
- dynamical systems