Multi-Robot Inverse Reinforcement Learning Under Occlusion with State Transition Estimation.
Kenneth D. BogertPrashant DoshiPublished in: AAMAS (2015)
Keyphrases
- multi robot
- state transition
- inverse reinforcement learning
- path planning
- state space
- multi robot systems
- input output
- state transitions
- black box
- mobile robot
- hidden markov models
- multi robot exploration
- reward function
- finite state machines
- markov chain
- preference elicitation
- probability distribution
- markov decision processes
- reinforcement learning
- robotic systems
- robot teams
- dynamic programming
- decision making