SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.02834 · ICML · 2025

Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks

Seungyul Han, Jeongmo Kim, Yisak Park, Minung Kim

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/2502.02834.json · badge: /api/ran/2502.02834.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
sunwoolee0504/wall community
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Block Ran
ran on a synthesized input · constructed an object; no result was computed
sunwoolee0504/wall/src/modules/step/models.py
code served (permissive licence) · get_code("0340d1b0f37688a5")
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 an instance of its own class, Block: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    'h_dim': 8,
    'max_T': 5,
    'n_heads': 2,
    'drop_p': 0.1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Block — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Block 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
MaskedCausalAttention Ran
ran on a synthesized input · constructed an object; no result was computed
sunwoolee0504/wall/src/modules/step/models.py
code served (permissive licence) · get_code("7a7dab71d814fea4")
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 an instance of its own class, MaskedCausalAttention: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

# Define parameters for MaskedCausalAttention
h_dim = 8  # hidden dimension, divisible by n_heads
max_T = 5  # maximum sequence length
n_heads = 2  # number of attention heads
drop_p = 0.1  # dropout probability

# Create a small input tensor for testing
# Shape: (batch_size, sequence_length, hidden_dim)
batch_size = 2
seq_length = 4
x = torch.randn(batch_size, seq_length, h_dim)

ARGS = {
    'h_dim': h_dim,
    'max_T': max_T,
    'n_heads': n_heads,
    'drop_p': drop_p
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MaskedCausalAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MaskedCausalAttention 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
Qdifference_Transformer Ran
ran on a synthesized input · constructed an object; no result was computed
sunwoolee0504/wall/src/modules/step/models.py
code served (permissive licence) · get_code("a3eb662536d508fd")
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 an instance of its own class, Qdifference_Transformer: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

class Args:
    def __init__(self):
        self.state_shape = 5
        self.trans_embed_dim = 8
        self.num_trans_layer = 2
        self.trans_input_len = 4
        self.num_trans_head = 2
        self.env_max_timestep = 10
        self.n_agents = 3
        self.attack_period = 6

ARGS = {
    'args': Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Qdifference_Transformer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Qdifference_Transformer 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

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
Block
brick of this paper's assembly: model
1 other paper
1 dated earlier
2106.01345 (2021-06)
Decision Transformer: Reinforcement Learning via Sequence Modeling
MaskedCausalAttention
brick of this paper's assembly: model
1 other paper
1 dated earlier · 1 only as an assembly brick
2106.01345 (2021-06)
Decision Transformer: Reinforcement Learning via Sequence Modeling

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

Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with out-of-distribution (OOD) tasks. To address this, we propose Task-Aware Virtual Training (TAVT), a novel algorithm that accurately captures task characteristics for both training and OOD scenarios using metricbased representation learning. Our method successfully preserves task characteristics in virtual tasks and employs a state regularization technique to mitigate overestimation errors in state-varying environments. Numerical results demonstrate that TAVT significantly enhances generalization to OOD tasks across various MuJoCo and Meta-World environments. Our code is available at https://github.com/JM-Kim-94/tavt.git.

For agents

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

get_harvested_code_for_paper("2502.02834")
get_code_for_paper("2502.02834")
have("2502.02834")

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

curl https://syntology.ai/api/ran/2502.02834.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.02834.svg)](https://syntology.ai/paper/2502.02834)

Connect an agent — have() is free.