Papers › Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning

26 Feb 2024arXiv:2402.16801archive 2025-07-28

Michael Matthews, Michael Beukman, Benjamin Ellis, Mikayel Samvelyan, Matthew Jackson, Samuel Coward, Jakob Foerster

Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms. We identify that existing benchmarks used for research into open-ended learning fall into one of two categories. Either they are too slow for meaningful research to be performed without enormous computational resources, like Crafter, NetHack and Minecraft, or they are not complex enough to pose a significant challenge, like Minigrid and Procgen. To remedy this, we first present Craftax-Classic: a ground-up rewrite of Crafter in JAX that runs up to 250x faster than the Python-native original. A run of PPO using 1 billion environment interactions finishes in under an hour using only a single GPU and averages 90% of the optimal reward. To provide a more compelling challenge we present the main Craftax benchmark, a significant extension of the Crafter mechanics with elements inspired from NetHack. Solving Craftax requires deep exploration, long term planning and memory, as well as continual adaptation to novel situations as more of the world is discovered. We show that existing methods including global and episodic exploration, as well as unsupervised environment design fail to make material progress on the benchmark. We believe that Craftax can for the first time allow researchers to experiment in a complex, open-ended environment with limited computational resources.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.16801")

Code

Syntology Ran 2 of 16 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

michaeltmatthews/craftax officialmentioned in papermentioned on GitHubjaxMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 2 ran; 0 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran
14unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from michaeltmatthews/craftax. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

achievement_mapping michaeltmatthews/craftax/craftax/craftax/constants.py official repository ran fingerprinted MIT (permissive) · 25c2020d2f7ef242 · report
apply_alpha michaeltmatthews/craftax/craftax/craftax/constants.py official repository ran MIT (permissive) · 4d0be89673d8cab0 · report
add_items_from_chest michaeltmatthews/craftax/craftax/craftax/game_logic.py official repository unverified MIT (permissive) · 04a2736c94bfb327 · report
in_bounds michaeltmatthews/craftax/craftax/craftax_classic/game_logic.py official repository unverified MIT (permissive) · 69f869f3f372b3a9 · report
is_game_over michaeltmatthews/craftax/craftax/craftax/game_logic.py official repository unverified MIT (permissive) · f92b11ac53caaa07 · report
is_game_over michaeltmatthews/craftax/craftax/craftax_classic/game_logic.py official repository unverified MIT (permissive) · 79fc8ae7f8130cd9 · report
is_in_wall michaeltmatthews/craftax/craftax/craftax_classic/game_logic.py official repository unverified MIT (permissive) · e0e34adbed9cddba · report
load_all_textures_given_size michaeltmatthews/craftax/craftax/craftax_classic/constants.py official repository unverified MIT (permissive) · 7bc9074fe028fcc0 · report
load_texture michaeltmatthews/craftax/craftax/craftax/constants.py official repository unverified MIT (permissive) · cac576950e78d45e · report
load_texture michaeltmatthews/craftax/craftax/craftax_classic/constants.py official repository unverified MIT (permissive) · 36d0610cd487a26d · report
make_craftax_env_from_name michaeltmatthews/craftax/craftax/craftax_env.py official repository unverified MIT (permissive) · 75146bd9aa6e42d1 · report
make_craftax_env_from_params michaeltmatthews/craftax/craftax/craftax_env.py official repository unverified MIT (permissive) · 2b99724b4cecd006 · report
make_craftax_pixel_renderer michaeltmatthews/craftax/craftax/craftax_classic/renderer.py official repository unverified MIT (permissive) · aa77320ddfdef78f · report
render_craftax_symbolic michaeltmatthews/craftax/craftax/craftax_classic/renderer.py official repository unverified MIT (permissive) · 07dd74360c9c3c54 · report
render_pixels_empty michaeltmatthews/craftax/craftax/craftax_classic/renderer.py official repository unverified MIT (permissive) · 828f715fe8506014 · report
update_plants_with_eat michaeltmatthews/craftax/craftax/craftax/game_logic.py official repository unverified MIT (permissive) · 7bb9713c73e31d70 · report

Tasks

MinecraftNetHackReinforcement LearningReinforcement Learning (RL)reinforcement-learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Entropy RegularizationPPO

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