Bounded Finite State Controllers

Dec-31-2004–Neural Information Processing Systems

We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic finite state controllers, combining several advantages of gradient ascent (efficiency, search through restricted controller space) and policy iteration (less vulnerability to local optima).

belief state, controller, node, (14 more...)

Neural Information Processing Systems

Dec-31-2004

Conferences PDF

Add feedback

Country:
- Oceania > Australia
  - New South Wales > Sydney (0.04)
- North America
  - Mexico (0.04)
  - United States
    - Wisconsin > Dane County
      - Madison (0.04)
    - Rhode Island > Providence County
      - Providence (0.04)
    - Oregon > Multnomah County
      - Portland (0.04)
  - Canada
    - Ontario > Toronto (0.30)
    - British Columbia > Metro Vancouver Regional District
      - Vancouver (0.04)
- Europe
  - Sweden > Stockholm
    - Stockholm (0.04)
  - Spain > Castilla-La Mancha
    - Toledo Province > Toledo (0.04)

Industry:
- Government > Regional Government > North America Government > United States Government (0.61)

Technology:
- Information Technology > Artificial Intelligence
  - Representation & Reasoning > Optimization (0.53)
  - Machine Learning > Learning Graphical Models
    - Undirected Networks > Markov Models (0.52)

Duplicate Docs Excel Report

Title
Bounded Finite State Controllers
Bounded Finite State Controllers

Similar Docs Excel Report more

Title	Similarity	Source
None found