Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization

Abstract

We propose a new stochastic primal-dual optimization algorithm for planning in a large discounted Markov decision process with a generative model and linear function approximation. Assuming that the feature map approximately satisfies standard realizability and Bellman-closedness conditions and also that the feature vectors of all state-action pairs are representable as convex combinations of a small core set of state-action pairs, we show that our method outputs a near-optimal policy after a polynomial number of queries to the generative model. Our method is computationally efficient and comes with the major advantage that it outputs a single softmax policy that is compactly represented by a low-dimensional parameter vector, and does not need to execute computationally expensive local planning subroutines in runtime.

Cite

Text

Neu and Okolo. "Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization." Proceedings of The 34th International Conference on Algorithmic Learning Theory, 2023.

Markdown

[Neu and Okolo. "Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization." Proceedings of The 34th International Conference on Algorithmic Learning Theory, 2023.](https://mlanthology.org/alt/2023/neu2023alt-efficient/)

BibTeX

@inproceedings{neu2023alt-efficient,
  title     = {{Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization}},
  author    = {Neu, Gergely and Okolo, Nneka},
  booktitle = {Proceedings of The 34th International Conference on Algorithmic Learning Theory},
  year      = {2023},
  pages     = {1101-1123},
  volume    = {201},
  url       = {https://mlanthology.org/alt/2023/neu2023alt-efficient/}
}