Bayesian Nonparametric Inverse Reinforcement Learning for Switched Markov Decision Processes.
Amit SuranaKunal SrivastavaPublished in: ICMLA (2014)
Keyphrases
- markov decision processes
- inverse reinforcement learning
- bayesian nonparametric
- reward function
- optimal policy
- reinforcement learning algorithms
- finite state
- partially observable
- markov decision process
- reinforcement learning
- state space
- dynamic programming
- policy iteration
- finite horizon
- infinite horizon
- average cost
- learning algorithm
- mixture model
- preference elicitation
- bayesian inference
- learning agent
- action space
- average reward
- multi agent