Adaptive Point-Based Value Iteration for Continuous States POMDP in Goal-Directed Imitation Learning
Autor: | Ferdian Adi Pratama, Nak Young Chong, Hosun Lee, Geunho Lee |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2012 |
Předmět: |
Mathematical optimization
Discretization Computer science Sequential Decision Making Partially observable Markov decision process Mobile robot POMDP Motion control Computer Science::Robotics Automated planning and scheduling State space Imitation Motion planning Motion Planning Curse of dimensionality |
Zdroj: | 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI). :249-254 |
Popis: | In motion planning and robot navigation, continuous domain would be the natural way of representation of state space. However, discretization is needed in order to deal with continuous state space. Results precision depends on the discretization, which leads to a problem of “curse of dimensionality”. We present a new approximation approach of goal-directed imitation learning algorithm using the point-based value iteration algorithm that deals with continuous domain in motion planning. We demonstrate our algorithm in the V-REP robot simulator, to validate the experimental result. |
Databáze: | OpenAIRE |
Externí odkaz: |