Papers › Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments

Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments

20 Jan 2021ICLR 2021 1arXiv:2101.08152archive 2025-07-28

Daochen Zha, Wenye Ma, Lei Yuan, Xia Hu, Ji Liu

Exploration under sparse reward is a long-standing challenge of model-free reinforcement learning. The state-of-the-art methods address this challenge by introducing intrinsic rewards to encourage exploration in novel states or uncertain environment dynamics. Unfortunately, methods based on intrinsic rewards often fall short in procedurally-generated environments, where a different environment is generated in each episode so that the agent is not likely to visit the same state more than once. Motivated by how humans distinguish good exploration behaviors by looking into the entire episode, we introduce RAPID, a simple yet effective episode-level exploration method for procedurally-generated environments. RAPID regards each episode as a whole and gives an episodic exploration score from both per-episode and long-term views. Those highly scored episodes are treated as good exploration behaviors and are stored in a small ranking buffer. The agent then imitates the episodes in the buffer to reproduce the past good exploration behaviors. We demonstrate our method on several procedurally-generated MiniGrid environments, a first-person-view 3D Maze navigation task from MiniWorld, and several sparse MuJoCo tasks. The results show that RAPID significantly outperforms the state-of-the-art intrinsic reward strategies in terms of sample efficiency and final performance. The code is available at https://github.com/daochenzha/rapid

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

Syntology holds a reference implementation of RAPID, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: 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.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='RAPID') (how to connect); the free check have('2101.08152') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 28 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 4 ran (2 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 23 samples from 1 repository, 10 ran (8 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 14 samples that ran have no recorded date.

daochenzha/rapid officialmentioned in papertfSyntology: 5 samples, 4 ran (2 instrument-failed) · 1 unverified report
maximecb/gym-miniworld officialmentioned in paperpytorchSyntology: not harvested report
aklein1995/exploration_sil_im mentioned on GitHubtfSyntology: 23 samples, 10 ran (2 instrument-failed) · 13 unverified 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

28 samples harvested: 14 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
2ran; the contract check could not run
9ran
14unverified

Licence: 0 of the 28 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

daochenzha/rapid official repository 5 samples, 4 ran (2 instrument-failed) · 1 unverified
Counter rapid/buffer.py ran · metamorphic tier: well formed MIT (permissive) · d6eaff6eabe8943b · report fixture: signature obs:list/1/ndarray · returned int · level recorded 2026-09-22
constfn in 10 papers rapid/agent.py ran · our draft was wrong MIT (permissive) · 8758308dc6c0727f · report fixture: signature val:int/0/int · returned function · level recorded, date not recorded
get_local_bonus rapid/buffer.py ran; the contract check could not run (RAISES) MIT (permissive) · 1bd23d9c5df7763c · report fixture: signature obs:ndarray/2/int, score_type:str/0/str · returned float · level recorded 2026-09-22
sf01 in 9 papers rapid/agent.py ran · violated contract MIT (permissive) · baf2a28d376d7803 · report fixture: signature arr:ndarray/4/float · returned ndarray · level recorded, date not recorded
RankingBuffer rapid/buffer.py unverified MIT (permissive) · c0f83827d6c75fca · report
aklein1995/exploration_sil_im community (archive-listed) 23 samples, 10 ran (2 instrument-failed) · 13 unverified
BeBold rapid/rapid_agent.py ran fingerprinted MIT (permissive) · ad5584bf82eab7fe · report fixture: signature obs:ndarray/2/float, nobs:ndarray/2/float · returned int · level recorded 2026-09-24
Counter rapid/rapid_agent.py ran MIT (permissive) · 978c689ae69157a3 · report fixture: returned Counter · level recorded 2026-09-22
HumanOutputFormat rapid/rapid_agent.py ran MIT (permissive) · 242a79b49bc8f5de · report fixture: returned HumanOutputFormat · level recorded 2026-09-22
JSONOutputFormat rapid/rapid_agent.py ran MIT (permissive) · 081800d1f215fd82 · report fixture: returned JSONOutputFormat · level recorded 2026-09-22
Logger in 25 papers rapid/rapid_agent.py ran MIT (permissive) · ecaf9ce3efa32820 · report fixture: returned Logger · level recorded 2026-09-22
explained_variance in 6 papers rapid/rapid_agent.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 6f9580f36835d52d · report fixture: signature ypred:ndarray/1/float, y:ndarray/1/float · returned float64 · level recorded 2026-09-22
get_current rapid/rapid_agent.py ran MIT (permissive) · f0b5e724afa08592 · report fixture: returned Logger · level recorded 2026-09-22
get_dir in 14 papers rapid/rapid_agent.py ran · metamorphic tier: deterministic MIT (permissive) · 19fa70dab4a7056f · report fixture: returned str · level recorded 2026-09-22
get_rank_without_mpi_import rapid/rapid_agent.py ran · metamorphic tier: well formed MIT (permissive) · 3c4301eba0f1aaf2 · report fixture: returned int · level recorded 2026-09-22
make_output_format in 88 papers rapid/rapid_agent.py ran · our draft was wrong MIT (permissive) · 8b7334946d2ed532 · report fixture: signature format:str/0/str, ev_dir:str/0/str, log_suffix:str/0/str · returned HumanOutputFormat · level recorded 2026-09-22
AbstractEnvRunner rapid/rapid_agent.py unverified MIT (permissive) · b21a3fc9290718d4 · report
CSVOutputFormat rapid/rapid_agent.py unverified MIT (permissive) · 0c58056d576d9ba8 · report
Model in 227 papers rapid/rapid_agent.py unverified MIT (permissive) · efd67c7b09262d14 · report
Runner rapid/rapid_agent.py unverified MIT (permissive) · b18fdb2df2966f99 · report
TensorBoardOutputFormat rapid/rapid_agent.py unverified MIT (permissive) · 07d722b0c7f269f6 · report
_configure_default_logger rapid/rapid_agent.py unverified MIT (permissive) · 5b226f8121d5718b · report
configure in 6 papers rapid/rapid_agent.py unverified MIT (permissive) · 819a51a05cef8459 · report
info in 11 papers rapid/rapid_agent.py unverified MIT (permissive) · b5664e29a5753d3d · report
learn_rapid rapid/rapid_agent.py unverified MIT (permissive) · e22453516d7e1e51 · report
limit_cuda_visible_devices rapid/rapid_agent.py unverified MIT (permissive) · 13289659b2b68f4f · report
make_session in 5 papers rapid/rapid_agent.py unverified MIT (permissive) · 8db9834e56303b87 · report
set_global_seeds rapid/rapid_agent.py unverified MIT (permissive) · cbb527600328539c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

3 assemblies on this paper: 2 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for RAPID (graph method: RAPID), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_episodic_exploration_score entry · level 3 · ran · honoured contract · ba84c1e446f076769a76cd95c154a5c0edcbc35740de80ee8ea492caec3b3dae

2 sibling assemblies for RAPID (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for RAPID (graph method: RAPID). 28 bricks; individually on a fixture: 13 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 15 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. learn_rapid entry · level 0 · unverified · e22453516d7e1e51
  2. Model model · level 0 · unverified · efd67c7b09262d14
  3. Runner sampler · level 0 · unverified · b18fdb2df2966f99
  4. constfn helper · level 1 · ran · our draft was wrong · 8758308dc6c0727f
  5. explained_variance helper · level 1 · ran; the contract check could not run (RAISES) · 6f9580f36835d52d
  6. get_dir helper · level 1 · ran · 19fa70dab4a7056f
  7. limit_cuda_visible_devices helper · level 0 · unverified · 13289659b2b68f4f
  8. safemean helper · level 1 · ran · honoured contract · a7b323241cd70612
  9. set_global_seeds helper · level 0 · unverified · cbb527600328539c
  10. make_session helper · level 0 · unverified · 8db9834e56303b87
  11. AbstractEnvRunner helper · level 0 · unverified · b21a3fc9290718d4
  12. BeBold helper · level 1 · ran · ad5584bf82eab7fe
  13. Counter helper · level 1 · ran · 978c689ae69157a3
  14. info helper · level 0 · unverified · b5664e29a5753d3d
  15. sf01 helper · level 1 · ran · violated contract · baf2a28d376d7803
  16. get_current helper · level 1 · ran · f0b5e724afa08592
  17. log helper · level 0 · unverified · 420a7935bc54a351
  18. Logger helper · level 1 · ran · ecaf9ce3efa32820
  19. _configure_default_logger helper · level 0 · unverified · 5b226f8121d5718b
  20. KVWriter helper · level 0 · unverified · 94eba517b065a1f9
  21. SeqWriter helper · level 0 · unverified · 75894be2cafb4f9a
  22. configure helper · level 0 · unverified · 819a51a05cef8459
  23. get_rank_without_mpi_import helper · level 1 · ran · 3c4301eba0f1aaf2
  24. make_output_format helper · level 1 · ran · our draft was wrong · 8b7334946d2ed532
  25. CSVOutputFormat helper · level 0 · unverified · 0c58056d576d9ba8
  26. HumanOutputFormat helper · level 1 · ran · 242a79b49bc8f5de
  27. JSONOutputFormat helper · level 1 · ran · 081800d1f215fd82
  28. TensorBoardOutputFormat helper · level 0 · unverified · 07d722b0c7f269f6

harvested Assembly for RAPID (graph method: RAPID). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. RankingBuffer entry · level 0 · unverified · c0f83827d6c75fca
  2. Counter helper · level 1 · ran · d6eaff6eabe8943b
  3. get_local_bonus metric · level 1 · ran; the contract check could not run (RAISES) · 1bd23d9c5df7763c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2101.08152") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

MuJoCo

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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