Successor Features Based Multi-Agent RL for Event-Based Decentralized MDPs.
Tarun GuptaAkshat KumarPraveen ParuchuriPublished in: AAAI (2019)
Keyphrases
- multi agent
- reinforcement learning
- markov decision processes
- cooperative
- state space
- feature space
- low level
- optimal policy
- image features
- dec pomdps
- learning agents
- function approximation
- autonomous agents
- multiagent systems
- machine learning
- classification accuracy
- feature vectors
- multi agent systems
- peer to peer
- linear programming
- dynamical systems
- dynamic programming
- finite state
- multiple agents
- model free
- feature extraction
- learning algorithm