SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.08898 · ICLR · 2024

Bridging State and History Representations: Understanding Self-Predictive RL

Benjamin Eysenbach, Tianwei Ni, Pierre-Luc Bacon, Erfan Seyedsalehi, Michel Ma, Clement Gehring, Aditya Mahajan

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2401.08898.json · badge: /api/ran/2401.08898.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
twni2016/self-predictive-rl canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
apply_transition Ran
ran; our contract draft was wrong, not the code
twni2016/self-predictive-rl/linear_code/replearn/learn.py
pointer only (licence: NONE) · get_code("d32e3bf521a45cc9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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.

convert_int_to_onehot Ran
ran, honoured the contract we drafted
twni2016/self-predictive-rl/minigrid_code/models.py
pointer only (licence: NONE) · get_code("e96a22e24051892b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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 Ran
ran, violated the contract we drafted
twni2016/self-predictive-rl/linear_code/experiments/plot.py
pointer only (licence: NONE) · get_code("86bdc9baa6659155")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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.

create_latent_encoder Ran
ran; our contract draft was wrong, not the code
twni2016/self-predictive-rl/linear_code/replearn/learn.py
pointer only (licence: NONE) · get_code("d9cccd149ff01a53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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.

profile Ran
ran; our contract draft was wrong, not the code
twni2016/self-predictive-rl/minigrid_code/logger.py
pointer only (licence: NONE) · get_code("09f2ec0dd993bee2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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.

put_in_middle Ran
ran; our contract draft was wrong, not the code
twni2016/self-predictive-rl/minigrid_code/logger.py
pointer only (licence: NONE) · get_code("8a7d4bf0997a2696")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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.

sum_rewards Ran
ran, violated the contract we drafted
twni2016/self-predictive-rl/minigrid_code/r2d2replaybuffer.py
pointer only (licence: NONE) · get_code("f5e9fc328ce0627b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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.

walk_through Ran
ran on a synthesized input
twni2016/self-predictive-rl/minigrid_code/vis_tool.py
pointer only (licence: NONE) · get_code("65a4b775f50a747f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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.

train Not yet run
unverified (harvested, no recorded run)
twni2016/self-predictive-rl/linear_code/replearn/learn.py
pointer only (licence: NONE) · get_code("db5b40218f291550")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twni2016/self-predictive-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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

FunctionAlso present inEarliest-datedOthers named
profile 13 other papers
13 dated earlier
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
1806.07857 (2018-06)
RUDDER: Return Decomposition for Delayed Rewards
and 10 more not named here

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

Representations are at the core of all deep reinforcement learning (RL) methods for both Markov decision processes (MDPs) and partially observable Markov decision processes (POMDPs). Many representation learning methods and theoretical frameworks have been developed to understand what constitutes an effective representation. However, the relationships between these methods and the shared properties among them remain unclear. In this paper, we show that many of these seemingly distinct methods and frameworks for state and history abstractions are, in fact, based on a common idea of self-predictive abstraction. Furthermore, we provide theoretical insights into the widely adopted objectives and optimization, such as the stop-gradient technique, in learning self-predictive representations. These findings together yield a minimalist algorithm to learn self-predictive representations for states and histories. We validate our theories by applying our algorithm to standard MDPs, MDPs with distractors, and POMDPs with sparse rewards. These findings culminate in a set of preliminary guidelines for RL practitioners. 1

For agents

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

get_harvested_code_for_paper("2401.08898")
get_code_for_paper("2401.08898")
have("2401.08898")

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

curl https://syntology.ai/api/ran/2401.08898.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.08898.svg)](https://syntology.ai/paper/2401.08898)

Connect an agent — have() is free.