Methods › Reinforcement Learning › Offline Reinforcement Learning Methods › URL

Umbrella Reinforcement Learning

URL

34 papers tagged archive 2025-07-28

Introduced by Egor E. Nuzhin et al. in Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A computationally efficient approach for solving hard nonlinear problems of reinforcement learning (RL). It combines umbrella sampling, from computational physics/chemistry, with optimal control methods. The approach is realized on the basis of neural networks, with the use of policy gradient. It outperforms, by computational efficiency and implementation universality, the available state-of-the-art algorithms, in application to hard RL problems with sparse reward, state traps and lack of terminal states. The proposed approach uses an ensemble of simultaneously acting agents, with a modified reward which includes the ensemble entropy, yielding an optimal exploration-exploitation balance.

PaperSource

In Syntology about another paper, arXiv:2103.13841: repository known, no verified implementation (declared_code; repositories: 5 listed of 5 in the graph, strongest link: official). About another paper: this answer is about arXiv:2103.13841, while the archive credits arXiv:2411.14117.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:2103.13841 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 20 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified (of 26 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 34 · with a code link: 16 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 34 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 34 of 34, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 50 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Contrastive Learning3
Benchmarking2
Classification2
Zero-Shot Learning2
zero-shot-classification2
3D Pedestrian Tracking1
Anomaly Detection1
Binary Classification1
Blocking1
Code Generation1
Computational Efficiency1
Decoder1
Disentanglement1
Diversity1
Efficient Exploration1
Feature Importance1
Graph Classification1
Graph Neural Network1
Image Retrieval1
Image Segmentation1

Usage over time archive 2025-07-28

Papers per year tagged with URL: 2024 to 2025, peak 25 25 0 2024: 9 papers 2024 2025: 25 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (34 dated). Bars are counts, not a trend claim.

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

Offline Reinforcement Learning Methods

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