Multi-Agent Pattern Formation: a Distributed Model-Free Deep Reinforcement Learning Approach.
Elhadji Amadou Oury DialloToshiharu SugawaraPublished in: IJCNN (2020)
Keyphrases
- model free
- reinforcement learning
- multi agent
- pattern formation
- function approximation
- reinforcement learning algorithms
- temporal difference
- policy iteration
- state space
- cellular automata
- reinforcement learning methods
- learning algorithm
- markov decision processes
- single agent
- policy evaluation
- optimal policy
- average reward
- dynamic programming
- potential field
- image processing
- supervised learning
- rl algorithms
- machine learning
- optimal control
- learning process