Pseudorehearsal in Actor-Critic Agents with Neural Network Function Approximation.
Vladimir MarochkoLeonard JohardManuel MazzaraLuca LongoPublished in: AINA (2018)
Keyphrases
- function approximation
- actor critic
- neural network
- reinforcement learning
- temporal difference
- radial basis function
- policy gradient
- function approximators
- multi agent systems
- multi agent
- multiple agents
- reinforcement learning algorithms
- artificial neural networks
- approximate dynamic programming
- neuro fuzzy
- model free
- learning tasks
- temporal difference learning
- single agent
- optimal control
- fuzzy logic
- action selection
- state space
- dynamic environments
- gradient method
- stochastic games
- recurrent neural networks
- learning agent
- genetic algorithm
- policy iteration
- learning experience
- optimal policy
- markov decision processes
- basis functions