Inverse Reinforcement Learning Based on Behaviors of a Learning Agent.
Shunsuke SakuraiShigeyuki ObaShin IshiiPublished in: ICONIP (1) (2015)
Keyphrases
- learning agent
- inverse reinforcement learning
- reward function
- selective perception
- reinforcement learning
- state space
- markov decision processes
- reinforcement learning algorithms
- multiple agents
- optimal policy
- learning algorithm
- transition probabilities
- learning capabilities
- solving problems
- preference elicitation
- learning process
- state variables
- learning tasks
- temporal difference
- multi agent systems
- maximum entropy
- domain knowledge
- random walk
- markov chain
- training set
- dynamic programming