Achieving Correlated Equilibrium by Studying Opponent's Behavior Through Policy-Based Deep Reinforcement Learning.
Kuo Chun TsaiZhu HanPublished in: IEEE Access (2020)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- agent receives
- markov decision process
- state space
- machine learning
- partially observable environments
- control policy
- real robot
- action selection
- learning algorithm
- policy gradient
- state action
- markov decision processes
- decision problems
- reinforcement learning algorithms
- computational complexity
- dynamic programming
- reinforcement learning problems
- actor critic
- function approximation
- rl algorithms
- control policies
- markov decision problems
- incomplete information
- multi agent reinforcement learning
- action space
- nash equilibrium
- optimal control
- finite state