Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning.
Georgios PapoudakisFilippos ChristianosArrasy RahmanStefano V. AlbrechtPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- multi agent
- state space
- non stationary
- multi agent environments
- function approximation
- intelligent agents
- single agent
- multi agent systems
- learning agents
- reinforcement learning agents
- temporal difference
- model free
- optimal control
- optimal policy
- cooperative
- autonomous agents
- software agents
- learning problems
- multiagent systems
- reinforcement learning algorithms
- agent oriented
- cooperative agents
- machine learning
- action selection
- markov decision processes
- learning algorithm
- supervised learning
- multi agent reinforcement learning
- dynamic programming
- neural network
- fitted q iteration