Papers › RL²: Fast Reinforcement Learning via Slow Reinforcement Learning

RL²: Fast Reinforcement Learning via Slow Reinforcement Learning

9 Nov 2016arXiv:1611.02779archive 2025-07-28

Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel

Deep reinforcement learning (deep RL) has been successful in learning sophisticated behaviors automatically; however, the learning process requires a huge number of trials. In contrast, animals can learn new tasks in just a few trials, benefiting from their prior knowledge about the world. This paper seeks to bridge this gap. Rather than designing a "fast" reinforcement learning algorithm, we propose to represent it as a recurrent neural network (RNN) and learn it from data. In our proposed method, RL², the algorithm is encoded in the weights of the RNN, which are learned slowly through a general-purpose ("slow") RL algorithm. The RNN receives all information a typical RL algorithm would receive, including observations, actions, rewards, and termination flags; and it retains its state across episodes in a given Markov Decision Process (MDP). The activations of the RNN store the state of the "fast" RL algorithm on the current (previously unseen) MDP. We evaluate RL² experimentally on both small-scale and large-scale problems. On the small-scale side, we train it to solve randomly generated multi-arm bandit problems and finite MDPs. After RL² is trained, its performance on new MDPs is close to human-designed algorithms with optimality guarantees. On the large-scale side, we test RL² on a vision-based navigation task and show that it scales up to high-dimensional problems.

PaperPDFCodeCode 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.

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

Code

Syntology 21 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 2 repositories, 11 ran (8 with no instrument failure; 3 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.

No sample is linked to this paper from 10 of its repositories that Syntology harvested for other papers:

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.

19 repositories listed; official and paper-mentioned ones first.

BBDrive/Meta-SGD-RL mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
GeorgeDUT/MetaRLSAS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
Octavio-Pappalardo/RL2-implementation-pytorch mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (1 instrument-failed) · 2 unverified report
Zhiwei-Z/PrompLimitTest mentioned on GitHubtfMITSyntology: not harvested report
Zhiwei-Z/SeqPromp mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
Zhiwei-Z/prompzzw mentioned on GitHubtfMITSyntology: not harvested report
aliengirlliv/teachable mentioned on GitHubSyntology: 16 samples, 8 ran (2 instrument-failed) · 8 unverified report
bay3s/rl-squared mentioned on GitHubpytorchSyntology: not harvested report
clrrrr/promp_plus mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
dragen1860/MAML-Pytorch-RL mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
edlanglois/relearn mentioned on GitHubpytorchLGPL-3.0Syntology: not harvested report
gomerudo/nas-dmrl mentioned on GitHubtfMITSyntology: not harvested report
iclavera/learning_to_adapt mentioned on GitHubtfSyntology: not harvested report
iclavera/meta-mb mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
jonasrothfuss/promp mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ProMP: Proximal Meta-Policy Search (arXiv:1810.06784; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified) and Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture (arXiv:2105.13524; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
shunzh/pytorch-maml-rl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
tristandeleu/pytorch-maml-rl mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling... (arXiv:2204.02877; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
RobvanGastel/meta-rl-algorithms pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Meta-Gradient Reinforcement Learning (arXiv:1805.09801; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
veds12/torch_rl_squared MITSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 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.

3ran · our draft was wrong
8ran
10unverified

Licence: 0 of the 21 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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Octavio-Pappalardo/RL2-implementation-pytorch community (archive-listed) 5 samples, 3 ran (1 instrument-failed) · 2 unverified
Meta_agent_actor agent_and_tbpttPPO.py ran MIT (permissive) · 792b0690a04ce3bc · report fixture: signature hidden_state:Tensor/2/float · returned tuple · level recorded 2026-09-24
Meta_agent_critic agent_and_tbpttPPO.py ran · metamorphic tier: invariant MIT (permissive) · 0379751da7748c2a · report fixture: signature hidden_state:Tensor/2/float · returned Tensor · level recorded 2026-09-22
layer_init in 46 papers agent_and_tbpttPPO.py ran · our draft was wrong MIT (permissive) · e01d3118f70d5b05 · report fixture: signature layer:callable/0/?, std:float/0/float, bias_const:float/0/float · returned Linear · level recorded 2026-09-22
Outer_loop_action_agent agent_and_tbpttPPO.py unverified MIT (permissive) · 59c573474692344b · report
collect_evaluation_data evaluation.py unverified MIT (permissive) · a31c91d734c04428 · report
aliengirlliv/teachable community (archive-listed) 16 samples, 8 ran (2 instrument-failed) · 8 unverified
DiagGaussianActor in 5 papers algos/ppo.py ran · metamorphic tier: deterministic MIT (permissive) · 11487404dfdc69d8 · report fixture: returned DiagGaussianActor · level recorded 2026-09-22
DictList algos/ppo.py ran · metamorphic tier: deterministic MIT (permissive) · c18fe21a87357f31 · report fixture: returned DictList · level recorded 2026-09-22
FiLM in 11 papers algos/ppo.py ran · metamorphic tier: deterministic MIT (permissive) · 4b03e68ac41174cf · report fixture: returned FiLM · level recorded 2026-09-22
ImageEmbedding algos/ppo.py ran · metamorphic tier: deterministic MIT (permissive) · 5ffb9bf347805c8e · report fixture: returned ImageEmbedding · level recorded 2026-09-22
InstrEmbedding algos/ppo.py ran · metamorphic tier: deterministic MIT (permissive) · 6552221c0b64c499 · report fixture: returned InstrEmbedding · level recorded 2026-09-22
Logger in 25 papers algos/ppo.py ran MIT (permissive) · 35fc183b2b26ff4a · report fixture: returned Logger · level recorded 2026-09-22
merge_dictlists algos/ppo.py ran · our draft was wrong MIT (permissive) · 2ab0cf0a97c81ba7 · report fixture: signature list_of_dictlists:list/1/dict · returned DictList · level recorded 2026-09-22
mlp in 108 papers algos/ppo.py ran · our draft was wrong MIT (permissive) · e26d482acf579f3e · report fixture: signature input_dim:int/0/int, hidden_dim:int/0/int, output_dim:int/0/int, hidden_depth:int/0/int, output_mod:callable/0/? · returned Sequential · level recorded 2026-09-22
Agent in 42 papers algos/ppo.py unverified MIT (permissive) · 0a776339f3429848 · report
ImageBOWEmbedding algos/ppo.py unverified MIT (permissive) · 62cdc662994fc6e1 · report
KVWriter algos/ppo.py unverified MIT (permissive) · 94eba517b065a1f9 · report
PPOAgent algos/ppo.py unverified MIT (permissive) · 26687176ddf9ce39 · report
SeqWriter algos/ppo.py unverified MIT (permissive) · 75894be2cafb4f9a · report
info in 11 papers algos/ppo.py unverified MIT (permissive) · 6665938be4c3f60c · report
log in 61 papers
census: 10 implementations from 16 papers, 7 distinct outputs on one shared input
algos/ppo.py unverified MIT (permissive) · d39457795cdad002 · report
weight_init in 73 papers algos/ppo.py unverified MIT (permissive) · 6a3b5d4c89f6aec7 · 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. 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. 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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for RL² (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for RL² (graph method: RL²). 16 bricks; individually on a fixture: 8 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. PPOAgent entry · level 0 · unverified · 26687176ddf9ce39
  2. Agent helper · level 0 · unverified · 0a776339f3429848
  3. DiagGaussianActor helper · level 1 · ran · 11487404dfdc69d8
  4. ImageEmbedding helper · level 1 · ran · 5ffb9bf347805c8e
  5. InstrEmbedding helper · level 1 · ran · 6552221c0b64c499
  6. info helper · level 0 · unverified · 6665938be4c3f60c
  7. log helper · level 0 · unverified · d39457795cdad002
  8. merge_dictlists helper · level 1 · ran · our draft was wrong · 2ab0cf0a97c81ba7
  9. mlp helper · level 1 · ran · our draft was wrong · e26d482acf579f3e
  10. weight_init helper · level 0 · unverified · 6a3b5d4c89f6aec7
  11. ImageBOWEmbedding helper · level 0 · unverified · 62cdc662994fc6e1
  12. FiLM helper · level 1 · ran · 4b03e68ac41174cf
  13. Logger helper · level 1 · ran · 35fc183b2b26ff4a
  14. DictList helper · level 1 · ran · c18fe21a87357f31
  15. KVWriter helper · level 0 · unverified · 94eba517b065a1f9
  16. SeqWriter helper · level 0 · unverified · 75894be2cafb4f9a

harvested Assembly for RL² (graph method: RL²). 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 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. Outer_loop_action_agent entry · level 0 · unverified · 59c573474692344b
  2. Meta_agent_actor model · level 1 · ran · 792b0690a04ce3bc
  3. Meta_agent_critic model · level 1 · ran · 0379751da7748c2a
  4. layer_init helper · level 1 · ran · our draft was wrong · e01d3118f70d5b05

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="1611.02779") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Deep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

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