Scalable Reinforcement Learning Policies for Multi-Agent Control.
Christopher D. HsuHeejin JeongGeorge J. PappasPratik ChaudhariPublished in: IROS (2021)
Keyphrases
- reinforcement learning
- multi agent
- control policy
- control policies
- control problems
- optimal policy
- reinforcement learning agents
- state space
- cooperative multi agent systems
- policy search
- markov decision process
- adaptive control
- optimal control
- learning algorithm
- cooperative
- function approximation
- control strategies
- robot control
- markov decision processes
- multiagent reinforcement learning
- learning agents
- reinforcement learning algorithms
- robotic control
- action selection
- control system
- multi agent reinforcement learning
- traffic signal control
- long run
- markov decision problems
- control method
- partially observable
- multiple agents
- learning process
- inverted pendulum
- dynamic programming
- reward function
- partially observable markov decision processes
- decision problems