Towards Decentralized Reinforcement Learning Architectures for Social Dilemmas.
Nicolas AnastassacosMirco MusolesiPublished in: AAMAS (2019)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- cooperative
- optimal policy
- distributed systems
- machine learning
- state space
- temporal difference
- peer to peer
- reinforcement learning algorithms
- optimal control
- decentralized control
- learning algorithm
- distributed agents
- markov decision processes
- multiagent reinforcement learning
- multi robot systems
- distributed constraint optimization
- multi agent reinforcement learning
- database
- information flow control
- partially observable
- long run
- supervised learning
- dynamic programming
- genetic algorithm
- neural network
- data sets
- real time