SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.02767 · 2021

RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 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/2111.02767.json · badge: /api/ran/2111.02767.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
google-research/rlds canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
build_episode Ran
ran on a synthesized input
google-research/rlds/rlds/rlds_types.py
code served (permissive licence) · get_code("7523ed9e58b99d98")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf

STEPS = 'steps'

# Create a small tf.data.Dataset with timestep dictionaries
def create_dataset():
    data = [
        {'action': 0, 'reward': 1.0, 'observation': [1, 2, 3, 4]},
        {'action': 1, 'reward': 0.5, 'observation': [2, 3, 4, 5]}
    ]
    dataset = tf.data.Dataset.from_generator(
        lambda: iter(data),
        output_signature={
            'action': tf.TensorSpec(shape=(), dtype=tf.int32),
            'reward': tf.TensorSpec(shape=(), dtype=tf.float32),
            'observation': tf.TensorSpec(shape=(4,), dtype=tf.int32)
        }
    )
    return dataset

steps = create_dataset()

metadata = {
    'episode_id': 42,
    'environment': 'CartPole-v1',
    'total_reward': 195.5,
    'num_steps': 2
}

ARGS = {
    'steps': steps,
    'metadata': metadata
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_step Ran
ran on a synthesized input
google-research/rlds/rlds/rlds_types.py
code served (permissive licence) · get_code("66034bb1ad94167e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Define arguments for build_step
observation = torch.randn(2, 4)  # Small tensor: batch=2, dim=4
action = torch.randn(2, 3)  # Small tensor: batch=2, dim=3 (different from observation)
reward = torch.randn(2, 1)  # Small tensor: batch=2, dim=1
discount = torch.randn(2, 1)  # Small tensor: batch=2, dim=1
is_terminal = [False, False]  # List of bools
is_first = [True, False]  # List of bools
is_last = [False, True]  # List of bools
metadata = {"episode_id": 42, "env_name": "test_env"}  # Optional metadata dict

ARGS = {
    "observation": observation,
    "action": action,
    "reward": reward,
    "discount": discount,
    "is_terminal": is_terminal,
    "is_first": is_first,
    "is_last": is_last,
    "metadata": metadata,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_valid_rlds_dataset Not yet run
unverified (harvested, no recorded run)
google-research/rlds/rlds/rlds_types.py
code served (permissive licence) · get_code("c3bf0cae15359af1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

We introduce RLDS (Reinforcement Learning Datasets), an ecosystem for recording, replaying, manipulating, annotating and sharing data in the context of Sequential Decision Making (SDM) including Reinforcement Learning (RL), Learning from Demonstrations, Offline RL or Imitation Learning. RLDS enables not only reproducibility of existing research and easy generation of new datasets, but also accelerates novel research. By providing a standard and lossless format of datasets it enables to quickly test new algorithms on a wider range of tasks. The RLDS ecosystem makes it easy to share datasets without any loss of information and to be agnostic to the underlying original format when applying various data processing pipelines to large collections of datasets. Besides, RLDS provides tools for collecting data generated by either synthetic agents or humans, as well as for inspecting and manipulating the collected data. Ultimately, integration with TFDS facilitates the sharing of RL datasets with the research community.

For agents

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

get_harvested_code_for_paper("2111.02767")
get_code_for_paper("2111.02767")
have("2111.02767")

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

curl https://syntology.ai/api/ran/2111.02767.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.02767.svg)](https://syntology.ai/paper/2111.02767)

Connect an agent — have() is free.