Scalable Reinforcement Learning Policies for Multi-Agent Control.
Christopher D. HsuHeejin JeongGeorge J. PappasPratik ChaudhariPublished in: CoRR (2020)
Keyphrases
- partially observable
- reinforcement learning
- multi agent
- control policies
- markov decision problems
- control policy
- control problems
- optimal policy
- reward function
- state space
- markov decision processes
- partially observable markov decision processes
- optimal control
- reinforcement learning agents
- control strategies
- policy search
- adaptive control
- function approximation
- infinite horizon
- temporal difference
- cooperative multi agent systems
- reinforcement learning algorithms
- markov decision process
- model free
- decentralized control
- machine learning
- hierarchical reinforcement learning
- multi agent environments
- transfer learning
- intelligent agents
- multi agent systems
- multi agent reinforcement learning
- cooperative
- robot control
- long run
- continuous state
- heterogeneous agents
- robotic systems
- learning algorithm
- traffic signal control