Inference Strategies for Solving Semi−Markov Decision Processes
Semi-Markov decision processes are used to formulate many control problems and also play a key role in hierarchical reinforcement learning. In this chapter we show how to translate the decision making problem into a form that can instead be solved by inference and learning techniques. In particular,...
| मुख्य लेखकों: | , |
|---|---|
| स्वरूप: | Book section |
| प्रकाशित: |
2012
|
| _version_ | 1826277783986241536 |
|---|---|
| author | Hoffman, M de Freitas, N |
| author_facet | Hoffman, M de Freitas, N |
| author_sort | Hoffman, M |
| collection | OXFORD |
| description | Semi-Markov decision processes are used to formulate many control problems and also play a key role in hierarchical reinforcement learning. In this chapter we show how to translate the decision making problem into a form that can instead be solved by inference and learning techniques. In particular, we will establish a formal connection between planning in semi-Markov decision processes and inference in probabilistic graphical models, then build on this connection to develop an expectation maximization (EM) algorithm for policy optimization in these models. |
| first_indexed | 2024-03-06T23:34:07Z |
| format | Book section |
| id | oxford-uuid:6d0fd16a-9c91-46a3-9f14-01660c094be9 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T23:34:07Z |
| publishDate | 2012 |
| record_format | dspace |
| spelling | oxford-uuid:6d0fd16a-9c91-46a3-9f14-01660c094be92022-03-26T19:15:17ZInference Strategies for Solving Semi−Markov Decision ProcessesBook sectionhttp://purl.org/coar/resource_type/c_3248uuid:6d0fd16a-9c91-46a3-9f14-01660c094be9Department of Computer Science2012Hoffman, Mde Freitas, NSemi-Markov decision processes are used to formulate many control problems and also play a key role in hierarchical reinforcement learning. In this chapter we show how to translate the decision making problem into a form that can instead be solved by inference and learning techniques. In particular, we will establish a formal connection between planning in semi-Markov decision processes and inference in probabilistic graphical models, then build on this connection to develop an expectation maximization (EM) algorithm for policy optimization in these models. |
| spellingShingle | Hoffman, M de Freitas, N Inference Strategies for Solving Semi−Markov Decision Processes |
| title | Inference Strategies for Solving Semi−Markov Decision Processes |
| title_full | Inference Strategies for Solving Semi−Markov Decision Processes |
| title_fullStr | Inference Strategies for Solving Semi−Markov Decision Processes |
| title_full_unstemmed | Inference Strategies for Solving Semi−Markov Decision Processes |
| title_short | Inference Strategies for Solving Semi−Markov Decision Processes |
| title_sort | inference strategies for solving semi markov decision processes |
| work_keys_str_mv | AT hoffmanm inferencestrategiesforsolvingsemimarkovdecisionprocesses AT defreitasn inferencestrategiesforsolvingsemimarkovdecisionprocesses |