Coordination in Adversarial Multi-Agent with Deep Reinforcement Learning Under Partial Observability.
Elhadji Amadou Oury DialloToshiharu SugawaraPublished in: ICTAI (2019)
Keyphrases
- partial observability
- multi agent
- reinforcement learning
- multi agent planning
- partially observable
- symbolic model checking
- multiagent systems
- partially observable markov decision processes
- cooperative
- multi agent systems
- multi agent reinforcement learning
- function approximation
- multiple agents
- agent programming
- state space
- fully observable
- markov decision process
- learning agent
- single agent
- reinforcement learning algorithms
- planning under partial observability
- planning problems
- markov decision processes
- autonomous agents
- hidden state
- dynamic programming
- learning algorithm
- machine learning
- belief space
- transfer learning
- optimal policy
- action selection
- model free
- supervised learning
- learning process