Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929370088603648 |
|---|---|
| author | Infante, Guillermo Jonsson, Anders Gómez, Vicenç |
| author_facet | Infante, Guillermo Jonsson, Anders Gómez, Vicenç |
| contents | In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the partitions. We represent value functions on several levels of abstraction, and use the compositionality of subtasks to estimate the optimal values of the states in each partition. The policy is implicitly defined on these optimal value estimates, rather than being decomposed among the subtasks. As a consequence, our approach can learn the globally optimal policy, and does not suffer from the non-stationarity of high-level decisions. If several partitions have equivalent dynamics, the subtasks of those partitions can be shared. If the set of boundary states is smaller than the entire state space, our approach can have significantly smaller sample complexity than that of a flat learner, and we validate this empirically in several experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_15380 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes Infante, Guillermo Jonsson, Anders Gómez, Vicenç Machine Learning Artificial Intelligence In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the partitions. We represent value functions on several levels of abstraction, and use the compositionality of subtasks to estimate the optimal values of the states in each partition. The policy is implicitly defined on these optimal value estimates, rather than being decomposed among the subtasks. As a consequence, our approach can learn the globally optimal policy, and does not suffer from the non-stationarity of high-level decisions. If several partitions have equivalent dynamics, the subtasks of those partitions can be shared. If the set of boundary states is smaller than the entire state space, our approach can have significantly smaller sample complexity than that of a flat learner, and we validate this empirically in several experiments. |
| title | Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2106.15380 |