Distributed Reinforcement Learning with ADMM-RL.
Peter A. GrafJennifer AnnoniChristopher J. BayDavid BiagioniDevon SiglerMonte LunacekWesley B. JonesPublished in: ACC (2019)
Keyphrases
- reinforcement learning
- multi agent
- reinforcement learning algorithms
- function approximation
- distributed systems
- model free
- temporal difference
- state space
- control problems
- action selection
- markov decision processes
- optimal policy
- learning algorithm
- learning problems
- distributed environment
- convex optimization
- machine learning
- peer to peer
- dynamic programming
- learning process
- cooperative
- reinforcement learning methods
- autonomous learning
- partially observable domains
- image restoration
- learning classifier systems
- mobile robot
- partially observable
- temporal difference learning
- multiagent reinforcement learning
- temporal difference methods
- direct policy search