Collaborative Multi-agent Reinforcement Learning for Landmark Localization Using Continuous Action Space.
Klemens KasserollerFranz ThalerChristian PayerDarko SternPublished in: IPMI (2021)
Keyphrases
- action space
- multi agent reinforcement learning
- landmark localization
- reinforcement learning
- state space
- markov decision processes
- multi agent
- single agent
- real valued
- stochastic games
- face detection
- continuous state spaces
- learning agents
- stochastic processes
- action selection
- learning agent
- function approximation
- multi agent systems
- temporal difference
- reinforcement learning algorithms
- supervised learning
- markov decision process
- cooperative
- learning algorithm
- learning process
- multi agent learning
- function approximators
- sufficient conditions
- optimal policy
- markov chain
- average reward
- mobile robot
- transfer learning
- multiple agents
- search algorithm
- optimal control