Single-Agent Policies for the Multi-Agent Persistent Surveillance Problem via Artificial Heterogeneity.
Thomas E. KentArthur RichardsAngus JohnsonPublished in: EUMAS/AT (2020)
Keyphrases
- single agent
- multi agent
- multiple agents
- multi agent systems
- multi agent environment
- optimal policy
- learning agents
- partially observable markov decision processes
- reinforcement learning
- multi agent coordination
- window search
- cooperative
- decision problems
- dynamic environments
- dec pomdps
- autonomous agents
- multiagent systems
- reward function
- action space
- control policies
- path finding
- stochastic games
- learning agent
- special case
- multiagent environments
- control policy
- decision making