Integrated Actor-Critic for Deep Reinforcement Learning.
Jiaohao ZhengMehmet Necip KurtXiaodong WangPublished in: ICANN (4) (2021)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- optimal control
- approximate dynamic programming
- gradient method
- function approximation
- neuro fuzzy
- policy gradient methods
- policy iteration
- state space
- markov decision processes
- learning algorithm
- natural actor critic
- machine learning
- evaluation function
- multi agent
- rl algorithms
- reinforcement learning methods
- temporal difference learning
- supervised learning
- cost function
- average reward
- function approximators
- control system
- control problems
- optimal policy
- transfer learning