Experiment of Cooperative Transportation using Multi-Robots by Multi-agent Deep Deterministic Policy Gradient.
Kazuhi MurataKenta MiyazakiNobutomo MatsunagaPublished in: ASCC (2022)
Keyphrases
- cooperative
- multi agent
- policy gradient
- single agent
- reinforcement learning
- multi agent systems
- mobile robot
- parametric optimization
- actor critic
- partially observable markov decision processes
- function approximation
- multiple agents
- optimal control
- game theory
- variance reduction
- neural network
- model free reinforcement learning