SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.08254 · 2019

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

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, 0 violated it and 2 have no contract verdict; 5 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/1903.08254.json · badge: /api/ran/1903.08254.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
junmokane/offline-PEARL community (classifier label)
classifier basis: plan_row
3 ran · 1 no recorded run
lujiayou123/Off-Policy-Meta-Reinforcement-Learning-via-Unsupervised-Domain-Translation community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
ido90/roml-pearl extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
victorchan314/cs287_final_project community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
create_stats_ordered_dict Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lujiayou123/Off-Policy-Meta-Reinforcement-Learning-via-Unsupervised-Domain-Translation/rlkit/core/eval_util.py
pointer only (licence: MIT); the stored copy get_code serves, from moreanp/csro, is pointer only (licence: NONE) · get_code("f395bfda2e4813d7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from moreanp/csro, and GitHub detected no licence in that repository 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.

cvar Ran
ran; our contract draft was wrong, not the code
ido90/roml-pearl/rlkit/core/rl_algorithm.py
pointer only (licence: NONE) · get_code("d8a2e44ea15298ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ido90/roml-pearl 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.

deep_update_dict Ran
ran; our contract draft was wrong, not the code
junmokane/offline-PEARL/launch_experiment.py
code served (permissive licence) · get_code("e937b70b07bfc9d1")
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) 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)

# Analyze the function:
# - deep_update_dict(fr, to) takes two parameters
# - It iterates over items in 'fr' dict
# - For each value, if it's a dict, recursively calls deep_update_dict(v, to[k])
# - Otherwise, updates to[k] = v
# - Returns the updated 'to' dict

# Construct test arguments:
# 'fr' should be a dict with nested dicts and scalar values
# 'to' should be a dict with matching structure to be updated

fr = {
    "model": {
        "learning_rate": 0.001,
        "batch_size": 32,
        "layers": {
            "hidden_dim": 128,
            "dropout": 0.5
        }
    },
    "training": {
        "epochs": 10,
        "optimizer": "adam"
    },
    "seed": 42
}

to = {
    "model": {
        "learning_rate": 0.01,
        "batch_size": 16,
        "layers": {
            "hidden_dim": 64,
            "dropout": 0.3
        }
    },
    "training": {
        "epochs": 5,
        "optimizer": "sgd"
    },
    "seed": 0
}

ARGS = {
    "fr": fr,
    "to": to
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
get_average_returns Ran
ran, honoured the contract we drafted
lujiayou123/Off-Policy-Meta-Reinforcement-Learning-via-Unsupervised-Domain-Translation/rlkit/core/eval_util.py
pointer only (licence: MIT); the stored copy get_code serves, from aviralkumar2907/CQL, is pointer only (licence: NONE) · get_code("a5d10a0b704c8db7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from aviralkumar2907/CQL, and GitHub detected no licence in that repository 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.

get_dim Ran
ran on a synthesized input
junmokane/offline-PEARL/rlkit/data_management/env_offline_replay_buffer.py
code served (permissive licence) · get_code("8a6359263de246f7")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np
from gym.spaces import Box, Discrete, Tuple

# Create test spaces for the get_dim function
box_space = Box(low=0, high=1, shape=(3, 4), dtype=np.float32)  # size = 12
discrete_space = Discrete(n=5)  # n = 5
nested_tuple_space = Tuple((
    Box(low=0, high=1, shape=(2,), dtype=np.float32),  # size = 2
    Discrete(n=3)  # n = 3
))

ARGS = {
    "space": box_space
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gym, numpy, rand_param_envs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
get_generic_path_information Ran
ran; our contract draft was wrong, not the code
lujiayou123/Off-Policy-Meta-Reinforcement-Learning-via-Unsupervised-Domain-Translation/rlkit/core/eval_util.py
pointer only (licence: MIT); the stored copy get_code serves, from moreanp/csro, is pointer only (licence: NONE) · get_code("c809703793017cd2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from moreanp/csro, and GitHub detected no licence in that repository 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.

get_mujoco_zip_name Ran
ran on a synthesized input
junmokane/offline-PEARL/docker/install_mujoco.py
code served (permissive licence) · get_code("3d87729bd4c217d5")
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 str. 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.

from distutils.version import LooseVersion

ARGS = {
    'platform': 'darwin',
    'version': '2.0.0'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
distutils — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
simple_separated_format Ran
ran; our contract draft was wrong, not the code
victorchan314/cs287_final_project/rlkit/core/tabulate.py
pointer only (licence: MIT); the stored copy get_code serves, from aviralkumar2907/CQL, is pointer only (licence: NONE) · get_code("5cb0c55f58279f59")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from aviralkumar2907/CQL, and GitHub detected no licence in that repository 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.

register_license Not yet run
unverified (harvested, no recorded run)
junmokane/offline-PEARL/rand_param_envs/mujoco_py/mjcore.py
code served (permissive licence) · get_code("5480531658d82335")
How it ran

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, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 7 later) and 2 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
simple_separated_format 27 other papers
27 later
1910.11670 (2019-10)
Contextual Imagined Goals for Self-Supervised Robotic Learning
1910.12827 (2019-10)
Entity Abstraction in Visual Model-Based Reinforcement Learning
1911.08453 (2019-11)
Planning with Goal-Conditioned Policies
and 24 more not named here
get_average_returns 24 other papers
24 later
1910.11670 (2019-10)
Contextual Imagined Goals for Self-Supervised Robotic Learning
1912.11032 (2019-12)
Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
2006.04779 (2020-06)
Conservative Q-Learning for Offline Reinforcement Learning
and 21 more not named here
deep_update_dict 13 other papers
13 later
2006.08170 (2020-06)
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
2009.13891 (2020-09)
Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
2010.01112 (2020-10)
FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization
and 10 more not named here
create_stats_ordered_dict 4 other papers
4 later
1912.11032 (2019-12)
Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
2206.03023 (2022-06)
Offline Goal-Conditioned Reinforcement Learning via f -Advantage Regression
2311.03695 (2023-11)
Context Shift Reduction for Offline Meta-Reinforcement Learning
and 1 more not named here
get_generic_path_information 3 other papers
3 later
2206.03023 (2022-06)
Offline Goal-Conditioned Reinforcement Learning via f -Advantage Regression
2311.03695 (2023-11)
Context Shift Reduction for Offline Meta-Reinforcement Learning
2502.03752 (2025-02)
Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning
register_license 3 other papers
3 later
2010.01112 (2020-10)
FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization
2311.03695 (2023-11)
Context Shift Reduction for Offline Meta-Reinforcement Learning
2312.15909 (2023-12)
Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations
get_mujoco_zip_name 2 other papers
2 later
2111.00134 (2021-11)
Context Meta-Reinforcement Learning via Neuromodulation
2502.03752 (2025-02)
Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning

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

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience, several major challenges preclude their practicality. Current methods rely heavily on on-policy experience, limiting their sample efficiency. The also lack mechanisms to reason about task uncertainty when adapting to new tasks, limiting their effectiveness in sparse reward problems. In this paper, we address these challenges by developing an off-policy meta-RL algorithm that disentangles task inference and control. In our approach, we perform online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience. This probabilistic interpretation enables posterior sampling for structured and efficient exploration. We demonstrate how to integrate these task variables with off-policy RL algorithms to achieve both meta-training and adaptation efficiency. Our method outperforms prior algorithms in sample efficiency by 20-100X as well as in asymptotic performance on several meta-RL benchmarks.

For agents

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

get_harvested_code_for_paper("1903.08254")
get_code_for_paper("1903.08254")
have("1903.08254")

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

curl https://syntology.ai/api/ran/1903.08254.json

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

[![Syntology run record](https://syntology.ai/api/ran/1903.08254.svg)](https://syntology.ai/paper/1903.08254)

Connect an agent — have() is free.