Adaptive Evolutionary Reinforcement Learning with Policy Direction.
Caibo DongDazi LiPublished in: Neural Process. Lett. (2024)
Keyphrases
- reinforcement learning
- optimal policy
- actor critic
- policy search
- function approximation
- action selection
- policy gradient
- partially observable environments
- state and action spaces
- markov decision processes
- function approximators
- partially observable
- reward function
- genetic algorithm
- state space
- evolutionary computation
- control policy
- markov decision process
- learning capabilities
- action space
- adaptive control
- model free
- approximate dynamic programming
- infinite horizon
- average cost
- policy making
- machine learning
- reinforcement learning problems
- agent learns
- temporal difference