Agent capability in persistent mission planning using approximate dynamic programming.
Brett BethkeJoshua D. ReddingJonathan P. HowMatthew A. VavrinaJohn VianPublished in: ACC (2010)
Keyphrases
- approximate dynamic programming
- mission planning
- linear program
- decision making
- dynamic programming
- reinforcement learning
- stochastic dynamic programming
- multi agent
- multi agent systems
- step size
- multiagent systems
- software agents
- autonomous agents
- control policy
- intelligent agents
- dynamic environments
- multiple agents
- linear programming
- machine learning
- action selection
- learning algorithm
- decision theoretic
- partially observable
- wavelet transform