Continuous Time Continuous Space Homeostatic Reinforcement Learning (CTCS-HRRL) : Towards Biological Self-Autonomous Agent.
Hugo LaurençonYesoda BhargavaRiddhi ZantyeCharbel-Raphaël SégerieJohann LussangeVeeky BathsBoris S. GutkinPublished in: CoRR (2024)
Keyphrases
- continuous space
- autonomous agents
- reinforcement learning
- multi agent
- state space
- optimal control
- discrete space
- dynamic environments
- reward signal
- multi agent systems
- mathematical morphology
- multiagent systems
- markov chain
- optimal policy
- reinforcement learning algorithms
- control architecture
- learning algorithm
- dynamical systems
- single agent
- spatial features
- markov decision processes
- dynamic programming
- image analysis
- high dimensional
- cooperative
- computer vision