Diversity Evolutionary Policy Deep Reinforcement Learning.
Jian LiuLiming FengPublished in: Comput. Intell. Neurosci. (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- reinforcement learning problems
- state and action spaces
- control policy
- partially observable
- actor critic
- control policies
- evolutionary process
- evolutionary computation
- partially observable environments
- function approximators
- action space
- reinforcement learning algorithms
- genetic algorithm
- markov decision processes
- model free
- reward function
- state space
- policy iteration
- rl algorithms
- policy evaluation
- function approximation
- dynamic programming
- policy gradient
- state action
- approximate dynamic programming
- partially observable domains
- control problems
- inverse reinforcement learning
- markov decision problems
- evolutionary algorithm
- continuous state spaces
- evolutionary methods
- learning algorithm
- policy gradient methods
- deep learning
- infinite horizon
- average reward
- supervised learning
- transfer learning
- temporal difference
- neural network
- agent learns
- evolutionary optimization
- continuous state
- long run
- search space
- optimal control
- partially observable markov decision processes
- transition model
- temporal difference learning
- decision problems
- multi agent reinforcement learning
- state dependent