Approximate Policy-Based Accelerated Deep Reinforcement Learning.
Xuesong WangYang GuYuhu ChengAiping LiuC. L. Philip ChenPublished in: IEEE Trans. Neural Networks Learn. Syst. (2020)
Keyphrases
- reinforcement learning
- policy evaluation
- optimal policy
- approximate policy iteration
- policy search
- temporal difference
- policy iteration
- markov decision processes
- action selection
- state space
- function approximation
- least squares
- markov decision process
- monte carlo
- model free
- reinforcement learning algorithms
- actor critic
- partially observable environments
- reinforcement learning problems
- function approximators
- policy gradient
- state action
- rl algorithms
- markov decision problems
- dynamic programming
- action space
- reward function
- control policy
- multi agent reinforcement learning
- sufficient conditions
- approximate dynamic programming
- state and action spaces
- robotic control
- learning algorithm
- control policies
- partially observable markov decision processes
- learning process
- multi agent
- machine learning
- average reward
- partially observable
- optimal control
- supervised learning
- policy gradient methods