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.
Papers archive 2025-07-28
16 shown of 16, 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.
-
Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models 24 May 2024 · 1 repository · arXiv:2405.15143Syntology ran 2 of 2 samples · 0 unverified
-
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 ran 1 of 3 samples · 2 unverified
-
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 ran 2 of 4 samples · 2 unverified · 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 ran 2 of 4 samples · 2 unverified · 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