Single Agent Indirect Herding via Approximate Dynamic Programming.
Patryk DeptulaZachary I. BellFederico M. ZegersRyan A. LicitraWarren E. DixonPublished in: CDC (2018)
Keyphrases
- approximate dynamic programming
- single agent
- reinforcement learning
- multi agent
- multiple agents
- multi agent systems
- dynamic environments
- linear program
- dynamic programming
- decision problems
- multi agent coordination
- path finding
- step size
- function approximation
- policy iteration
- action space
- state space
- optimal policy
- learning algorithm
- partially observable
- cooperative
- probability distribution
- bayesian networks
- control policy
- machine learning