Multi User Learning Agent on the Distribution of MDPs.
Daisuke KatagamiKatsumi NittaKazuteru MiyazakiPublished in: RO-MAN (2006)
Keyphrases
- multi user
- learning agent
- reinforcement learning
- state space
- markov decision processes
- reward function
- virtual environment
- virtual world
- augmented reality
- user interface
- single user
- reinforcement learning algorithms
- multiple users
- solving problems
- selective perception
- learning capabilities
- probability distribution
- virtual reality
- knowledge acquisition
- learning algorithm
- learning tasks
- state variables
- decision problems
- heuristic search
- optimal policy
- fuzzy sets
- np hard