Optimization for Reinforcement Learning: From a single agent to cooperative agents.
Donghwan LeeNiao HeParameswaran KamalarubanVolkan CevherPublished in: IEEE Signal Process. Mag. (2020)
Keyphrases
- single agent
- multi agent
- cooperative agents
- reinforcement learning
- learning agents
- multi agent systems
- multiple agents
- action space
- multiagent learning
- cooperative
- dynamic environments
- multiagent systems
- decision problems
- learning agent
- intelligent agents
- agent programming
- autonomous agents
- state space
- stochastic games
- path finding
- optimal policy
- reinforcement learning algorithms
- optimal solution
- software agents
- markov decision processes
- learning algorithm