Methods › Reinforcement Learning › Behaviour Policies › Go-Explore
Go-Explore
Introduced by Adrien Ecoffet et al. in Go-Explore: a New Approach for Hard-Exploration Problems
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Go-Explore is a family of algorithms aiming to tackle two challenges with effective exploration in reinforcement learning: algorithms forgetting how to reach previously visited states ("detachment") and from failing to first return to a state before exploring from it ("derailment").
To avoid detachment, Go-Explore builds an archive of the different states it has visited in the environment, thus ensuring that states cannot be forgotten. Starting with an archive beginning with the initial state, the archive is built iteratively. In Go-Explore we:
(a) Probabilistically select a state from the archive, preferring states associated with promising cells.
(b) Return to the selected state, such as by restoring simulator state or by running a goal-conditioned policy.
(c) Explore from that state by taking random actions or sampling from a trained policy.
(d) Map every state encountered during returning and exploring to a low-dimensional cell representation.
(e) Add states that map to new cells to the archive and update other archive entries.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1901.10995'). Repositories: 3 listed of 3 in the graph, strongest link: mentioned on GitHub. The lookup matched a paper by its title, arXiv:1901.10995, not a method entry. This answer is about arXiv:1901.10995, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1901.10995 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence). 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: 16 · with a code link: 5 · where Syntology ran a sample: 4 (2 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 16 tagged: 2 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 16 of 16, 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.
-
Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models 24 May 2024 · 1 repository · arXiv:2405.15143Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
Go-Explore for Residential Energy Management 15 Jan 2024 · 0 repositories · arXiv:2401.07710
-
Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning 21 Feb 2023 · 0 repositories · arXiv:2302.10825
-
Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm 13 Jan 2023 · 1 repository · arXiv:2301.05635Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)
-
First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation 6 Dec 2022 · 0 repositories · arXiv:2212.03251
-
Quality-diversity in dissimilarity spaces 14 Nov 2022 · 0 repositories · arXiv:2211.12337
-
Go-Explore Complex 3D Game Environments for Automated Reachability Testing 1 Sep 2022 · 0 repositories · arXiv:2209.00570
-
Cell-Free Latent Go-Explore 31 Aug 2022 · 1 repository · arXiv:2208.14928
-
Generative Personas That Behave and Experience Like Humans 26 Aug 2022 · 0 repositories · arXiv:2209.00459
-
Play with Emotion: Affect-Driven Reinforcement Learning 26 Aug 2022 · 0 repositories · arXiv:2208.12622
-
When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation 29 Mar 2022 · 0 repositories · arXiv:2203.16311
-
Go-Blend behavior and affect 24 Sep 2021 · 0 repositories · arXiv:2109.13388
-
First return, then explore 27 Apr 2020 · 2 repositories · arXiv:2004.12919Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
Adaptive Stress Testing without Domain Heuristics using Go-Explore 8 Apr 2020 · 0 repositories · arXiv:2004.04292
-
Exploration Based Language Learning for Text-Based Games 24 Jan 2020 · 0 repositories · arXiv:2001.08868
-
Go-Explore: a New Approach for Hard-Exploration Problems 30 Jan 2019 · 3 repositories · arXiv:1901.10995Syntology 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)
Tasks archive 2025-07-28
19 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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