Papers › Self-Supervised Policy Adaptation during Deployment

Self-Supervised Policy Adaptation during Deployment

8 Jul 2020ICLR 2021 1arXiv:2007.04309archive 2025-07-28

Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang

In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new environment, we assume no prior knowledge of those changes yet still obtain significant improvements. Empirical evaluations are performed on diverse simulation environments from DeepMind Control suite and ViZDoom, as well as real robotic manipulation tasks in continuously changing environments, taking observations from an uncalibrated camera. Our method improves generalization in 31 out of 36 environments across various tasks and outperforms domain randomization on a majority of environments.

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.

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

Code

Syntology 21 code samples: 19 from 2 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 21: 16 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 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: community (archive-listed): 19 samples from 2 repositories, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 16 samples that ran have no recorded date.

joshnroy/contrastive-pad mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
nicklashansen/policy-adaptation-during-deployment mentioned on GitHubpytorchSyntology: 16 samples, 12 ran (3 instrument-failed) · 4 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

21 samples harvested: 16 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 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.

4ran · our draft was wrong
2ran; the contract check could not run
10ran
5unverified

Licence: 21 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. 2 samples are listed last, in a group without a repository. “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 4 samples 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.

joshnroy/contrastive-pad community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
BarlowFunction src/agent/agent.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 554f154e05c8c199 · report fixture: returned BarlowFunction · level recorded 2026-09-22
aug in 8 papers src/agent/agent.py ran · our draft was wrong no licence file found · pointer only · e432c8c8eddcb3b7 · report fixture: signature x:Tensor/4/float, augs:callable/0/? · returned Tensor · level recorded 2026-09-22
SacSSAgent src/agent/agent.py unverified no licence file found · pointer only · b79c90b2fd9d2a85 · report
nicklashansen/policy-adaptation-during-deployment community (archive-listed) 16 samples, 12 ran (3 instrument-failed) · 4 unverified
Actor in 68 papers src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · d526a377580646ff · report fixture: returned Actor · level recorded 2026-09-22
CURL src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · 75b91cb1cba4f86b · report fixture: returned CURL · level recorded 2026-09-22
CenterCrop src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · 16eb246116ba494b · report fixture: returned CenterCrop · level recorded 2026-09-22
Critic in 60 papers src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · e70accfa4161d131 · report fixture: returned Critic · level recorded 2026-09-22
InvFunction src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · fb1526043e3ddf0f · report fixture: returned InvFunction · level recorded 2026-09-22
NormalizeImg src/agent/agent.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 21c9f18b03dc202c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
PixelEncoder in 5 papers src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · 77cffce9f453998c · report fixture: returned PixelEncoder · level recorded 2026-09-22
QFunction src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5447123791608219 · report fixture: returned QFunction · level recorded 2026-09-22
RotFunction src/agent/agent.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1e6ff078220508ca · report fixture: returned RotFunction · level recorded 2026-09-22
_rotate_single_with_label src/agent/agent.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 1a680b614b0ffdb5 · report fixture: signature x:Tensor/3/float, label:int/0/int · returned Tensor · level recorded 2026-09-22
make_encoder in 15 papers src/agent/agent.py ran · our draft was wrong no licence file found · pointer only · 6dcb9b4b8ec4aabd · report fixture: signature obs_shape:tuple/1/int, feature_dim:int/0/int, num_layers:int/0/int, num_filters:int/0/int, num_shared_layers:int/0/int · returned PixelEncoder · level recorded 2026-09-22
rotate in 56 papers src/agent/agent.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 638f9c8f01f54ad1 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
SacSSAgent src/agent/agent.py unverified no licence file found · pointer only · 6563fe457e0a49ef · report
soft_update_params src/agent/agent.py unverified no licence file found · pointer only · bc0768cc0f4f49c7 · report
tie_weights src/agent/agent.py unverified no licence file found · pointer only · fc88ef6a629962e5 · report
weight_init in 73 papers src/agent/agent.py unverified no licence file found · pointer only · 48b3228cfe8d98ae · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
gaussian_logprob in 17 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · daa7b3a0355eb7c3 · report fixture: signature noise:Tensor/2/float, log_std:Tensor/2/float · returned Tensor · level recorded, date not recorded
squash in 30 papers
census: 8 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · e4f442d1770eacd1 · report fixture: signature mu:Tensor/2/float, pi:Tensor/2/float, log_pi:Tensor/2/float · returned tuple · level recorded, date not recorded

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 SELF-SUPERVISED POLICY ADAPTATION (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for SELF-SUPERVISED POLICY ADAPTATION (graph method: SELF-SUPERVISED POLICY ADAPTATION). 18 bricks; individually on a fixture: 14 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. SacSSAgent entry · level 0 · unverified · 6563fe457e0a49ef
  2. Actor model · level 1 · ran · d526a377580646ff
  3. CURL loss · level 1 · ran · 75b91cb1cba4f86b
  4. Critic model · level 1 · ran · e70accfa4161d131
  5. InvFunction model · level 1 · ran · fb1526043e3ddf0f
  6. RotFunction model · level 1 · ran · 1e6ff078220508ca
  7. make_encoder helper · level 1 · ran · our draft was wrong · 6dcb9b4b8ec4aabd
  8. rotate helper · level 1 · ran; the contract check could not run (RAISES) · 638f9c8f01f54ad1
  9. soft_update_params helper · level 0 · unverified · bc0768cc0f4f49c7
  10. weight_init helper · level 0 · unverified · 48b3228cfe8d98ae
  11. gaussian_logprob helper · level 1 · ran · our draft was wrong · daa7b3a0355eb7c3
  12. squash helper · level 1 · ran · our draft was wrong · e4f442d1770eacd1
  13. QFunction model · level 1 · ran · 5447123791608219
  14. PixelEncoder helper · level 1 · ran · 77cffce9f453998c
  15. _rotate_single_with_label helper · level 1 · ran; the contract check could not run (RAISES) · 1a680b614b0ffdb5
  16. CenterCrop helper · level 1 · ran · 16eb246116ba494b
  17. NormalizeImg helper · level 1 · ran · 21c9f18b03dc202c
  18. tie_weights helper · level 0 · unverified · fc88ef6a629962e5

harvested Assembly for SELF-SUPERVISED POLICY ADAPTATION (graph method: SELF-SUPERVISED POLICY ADAPTATION). 20 bricks; individually on a fixture: 16 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. SacSSAgent entry · level 0 · unverified · b79c90b2fd9d2a85
  2. Actor model · level 1 · ran · d526a377580646ff
  3. BarlowFunction model · level 1 · ran · 554f154e05c8c199
  4. CURL model · level 1 · ran · 75b91cb1cba4f86b
  5. Critic model · level 1 · ran · e70accfa4161d131
  6. InvFunction model · level 1 · ran · fb1526043e3ddf0f
  7. RotFunction model · level 1 · ran · 1e6ff078220508ca
  8. aug helper · level 1 · ran · our draft was wrong · e432c8c8eddcb3b7
  9. make_encoder helper · level 1 · ran · our draft was wrong · 6dcb9b4b8ec4aabd
  10. rotate helper · level 1 · ran; the contract check could not run (RAISES) · 638f9c8f01f54ad1
  11. soft_update_params helper · level 0 · unverified · bc0768cc0f4f49c7
  12. weight_init helper · level 0 · unverified · 48b3228cfe8d98ae
  13. gaussian_logprob helper · level 1 · ran · our draft was wrong · daa7b3a0355eb7c3
  14. squash helper · level 1 · ran · our draft was wrong · e4f442d1770eacd1
  15. QFunction model · level 1 · ran · 5447123791608219
  16. PixelEncoder helper · level 1 · ran · 77cffce9f453998c
  17. _rotate_single_with_label helper · level 1 · ran; the contract check could not run (RAISES) · 1a680b614b0ffdb5
  18. CenterCrop helper · level 1 · ran · 16eb246116ba494b
  19. NormalizeImg helper · level 1 · ran · 21c9f18b03dc202c
  20. tie_weights helper · level 0 · unverified · fc88ef6a629962e5

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="2007.04309") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamDense ConnectionsExperience ReplayReLUSoft Actor-Critic (Autotuned Temperature)

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