Scaling Expectation-Maximization for Inverse Reinforcement Learning to Multiple Robots under Occlusion.
Kenneth D. BogertPrashant DoshiPublished in: AAMAS (2017)
Keyphrases
- k means
- expectation maximization
- multiple robots
- inverse reinforcement learning
- path planning
- em algorithm
- multi robot
- mobile robot
- autonomous robots
- preference elicitation
- collision avoidance
- mixture model
- ant colony
- reward function
- software agents
- generative model
- multiple targets
- cooperative
- neural network
- learning algorithm
- search algorithm
- topological map
- machine learning
- indoor environments
- ant colony optimization
- probabilistic model