Multi-robot inverse reinforcement learning under occlusion with estimation of state transitions.
Kenneth D. BogertPrashant DoshiPublished in: Artif. Intell. (2018)
Keyphrases
- multi robot
- state transitions
- inverse reinforcement learning
- state transition
- path planning
- multi robot systems
- mobile robot
- multi robot exploration
- preference elicitation
- multiple robots
- state action
- robot teams
- robotic systems
- reward function
- black box
- hidden markov models
- machine learning
- multi robot cooperative
- multi robot coordination
- input output
- markov chain
- search space
- decision making