SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.09396 · ICML · 2026

Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning

Sarath Chandar, Nilaksh, Antoine Clavaud, Franc ¸ois Rivest, Mathieu Reymond

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 3 failures of our instrument; 5 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.09396.json · badge: /api/ran/2602.09396.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
chandar-lab/stream-rep-rl community
Papers with Code archive
5 ran · 5 no recorded run
FunctionStatusWhere it lives
Args Ran
ran on a synthesized input · constructed an object; no result was computed
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("a725ce42033cbe35")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_lecun_uniform Ran
ran; our contract draft was wrong, not the code
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("61cc591f23ec3a80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cosine_similarity_loss Ran
ran, violated the contract we drafted
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("ef125192cc75c3e6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ema_update Ran
ran; our contract draft was wrong, not the code
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("fb23190491119f4f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sparse_init Ran
ran; our contract draft was wrong, not the code
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("4eff42a2348a3b27")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AgentState Not yet run
unverified (harvested, no recorded run)
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("df6d51b074eff1ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Config Not yet run
unverified (harvested, no recorded run)
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("1e66591052245215")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

layer_norm Not yet run
unverified (harvested, no recorded run)
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("b20d0377d799a4b6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

scale Not yet run
unverified (harvested, no recorded run)
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("7734e55467a4be79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

update_step_dqn Not yet run
unverified (harvested, no recorded run)
chandar-lab/stream-rep-rl/algorithms/dqn-spr.py
pointer only (licence: NONE) · get_code("dfd660d7d79c2ce5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chandar-lab/stream-rep-rl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-inefficient, since valuebased losses alone struggle to extract meaningful representations from transient data. We propose extending Self-Predictive Representations (SPR) to the streaming pipeline to maximize the utility of every observed frame. However, due to the highly correlated samples induced by the streaming regime, naively applying this auxiliary loss results in training instabilities. Thus, we introduce orthogonal gradient updates relative to the momentum target and resolve gradient conflicts arising from streaming-specific optimizers. Validated across the Atari, MinAtar, and Octax suites, our approach systematically outperforms existing streaming baselines. Latent-space analysis, including t-SNE visualizations and effective-rank measurements, confirms that our method learns significantly richer representations, bridging the performance gap caused by the absence of a replay buffer, while remaining efficient enough to train on just a few CPU cores 1 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.09396")
get_code_for_paper("2602.09396")
have("2602.09396")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.09396.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.09396.svg)](https://syntology.ai/paper/2602.09396)

Connect an agent — have() is free.