Pseudorehearsal in actor-critic agents with neural network function approximation.
Vladimir MarochkoLeonard JohardManuel MazzaraLuca LongoPublished in: CoRR (2017)
Keyphrases
- function approximation
- actor critic
- neural network
- reinforcement learning
- temporal difference
- radial basis function
- policy gradient
- function approximators
- multi agent
- multi agent systems
- multiple agents
- reinforcement learning algorithms
- model free
- temporal difference learning
- gradient method
- learning agent
- policy iteration
- optimal control
- action selection
- learning tasks
- artificial neural networks
- neuro fuzzy
- single agent
- recurrent neural networks
- fuzzy logic
- adaptive control
- markov decision processes
- semi supervised learning
- machine learning