Decentralised Active Perception in Continuous Action Spaces for the Coordinated Escort Problem.
Rhett HullKi Myung Brian LeeJennifer WakuliczChanyeol YooJames McMahonBryan ClarkeStuart AnsteeJijoong KimRobert FitchPublished in: CoRR (2023)
Keyphrases
- action space
- state space
- markov decision processes
- real valued
- continuous action
- reinforcement learning
- control policies
- continuous state
- state and action spaces
- single agent
- continuous state spaces
- multi agent
- skill learning
- stochastic processes
- cooperative
- action selection
- dynamic programming
- decision making
- multiple agents
- markov decision process
- reward function
- latent variables
- markov chain
- search algorithm
- image segmentation