AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning.
Wangyang YueYuan ZhouXiaochuan ZhangYuchen HuaZhiyuan WangGuang KouPublished in: CoRR (2022)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- approximate dynamic programming
- policy gradient
- optimal control
- reinforcement learning algorithms
- function approximation
- policy iteration
- neuro fuzzy
- gradient method
- dynamic programming
- markov decision processes
- model free
- state space
- average reward
- temporal difference learning
- rl algorithms
- natural actor critic
- machine learning
- evaluation function
- control problems
- function approximators
- optimal policy
- policy gradient methods
- step size
- dynamical systems
- transfer learning
- monte carlo
- multi agent