Methods › Reinforcement Learning › Policy Gradient Methods › MDPO
Mirror Descent Policy Optimization
MDPO
Introduced by Manan Tomar et al. in Mirror Descent Policy Optimization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Mirror Descent Policy Optimization (MDPO) is a policy gradient algorithm based on the idea of iteratively solving a trust-region problem that minimizes a sum of two terms: a linearization of the standard RL objective function and a proximity term that restricts two consecutive updates to be close to each other. It is based on Mirror Descent, which is a general trust region method that attempts to keep consecutive iterates close to each other.
Papers archive 2025-07-28
4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Fast Convergence of Softmax Policy Mirror Ascent 18 Nov 2024 · 0 repositories · arXiv:2411.12042
-
mDPO: Conditional Preference Optimization for Multimodal Large Language Models 17 Jun 2024 · 1 repository · arXiv:2406.11839Syntology ran 5 of 10 samples · 5 unverified · 10 pointer-only (licence)
-
Model-Based Decentralized Policy Optimization 16 Feb 2023 · 0 repositories · arXiv:2302.08139
-
Mirror Descent Policy Optimization 20 May 2020 · 1 repository · arXiv:2005.09814
Tasks archive 2025-07-28
9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Continuous Control | 1 |
| Hallucination | 1 |
| Language Modeling | 1 |
| Language Modelling | 1 |
| Large Language Model | 1 |
| MuJoCo | 1 |
| Reinforcement Learning (RL) | 1 |
| continuous-control | 1 |
| model | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections