SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.03310 · 2023

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 3 have no contract verdict; 1 failure of our instrument; 2 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/2306.03310.json · badge: /api/ran/2306.03310.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
HarryLui98/DMPEL community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
lifelong-robot-learning/libero community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
merge_datas Ran
ran on a synthesized input
HarryLui98/DMPEL/libero/lifelong/algos/er.py
code served (permissive licence) · get_code("3f3974d9ae10641b")
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 collections
import torch

torch.manual_seed(0)

# Create test data structures with nested dicts and tensors
x = {
    "tensor_float": torch.FloatTensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]]),
    "tensor_long": torch.LongTensor([[1, 2, 3, 4], [5, 6, 7, 8]]),
    "nested": {
        "inner_float": torch.FloatTensor([[0.1, 0.2, 0.3, 0.4]]),
        "inner_long": torch.LongTensor([[10, 20, 30, 40]])
    }
}

y = {
    "tensor_float": torch.FloatTensor([[9.0, 10.0, 11.0, 12.0]]),
    "tensor_long": torch.LongTensor([[9, 10, 11, 12]]),
    "nested": {
        "inner_float": torch.FloatTensor([[0.5, 0.6, 0.7, 0.8]]),
        "inner_long": torch.LongTensor([[50, 60, 70, 80]])
    }
}

ARGS = {
    "x": x,
    "y": y
}
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 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
project Ran
ran; our contract draft was wrong, not the code
HarryLui98/DMPEL/libero/lifelong/algos/agem.py
code served (permissive licence) · get_code("5d65b508e8b1cbad")
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 Tensor, ndim 1, dtype family float, shape (4,) 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 torch

torch.manual_seed(0)

# Create two small distinct 1D tensors for the function
# gxy and ger are used with torch.dot() so they need to be 1D tensors
# Using different sizes to make dimensions unambiguous
gxy = torch.randn(4)
ger = torch.randn(4)

ARGS = {
    "gxy": gxy,
    "ger": ger,
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
reshape_transform Ran
ran on a synthesized input
HarryLui98/DMPEL/libero/lifelong/models/bc_foundation_dmpel_policy.py
code served (permissive licence) · get_code("002c05cdb4cfb345")
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 Tensor, ndim 4, dtype family float, shape (2, 5, 3, 4) 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Analyze the function:
# - tensor: shape (B, _, E) where B is batch, second dim is sequence length (at least 1 + h*w),
#           E is embedding dimension
# - h: height for reshape
# - w: width for reshape
# The function extracts tensor[:, 1:1+h*w, :], reshapes to (B, h, w, E), then permutes to (B, E, h, w)

# Create a small tensor with distinct dimensions
# B=2 (batch), sequence_length needs to be at least 1+h*w
# Let's use h=3, w=4, so we need at least 1+12=13 in dimension 1
# E=5 (embedding)
B = 2
h = 3
w = 4
seq_len = 1 + h * w + 2  # 1 + 12 + 2 = 15 (with some buffer)
E = 5

tensor = torch.randn(B, seq_len, E)

ARGS = {
    "tensor": tensor,
    "h": h,
    "w": w,
}
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 Tensor, ndim 4, dtype family float, shape (2, 5, 3, 4) — shape (2, 5, 3, 4) 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
shasum_file Ran
ran on a synthesized input
HarryLui98/DMPEL/benchmark_scripts/shasum_files.py
code served (permissive licence) · get_code("372d77615649dce0")
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 os
import hashlib
import tempfile

# Create a temporary file with some content
temp_dir = tempfile.mkdtemp()
temp_file_path = os.path.join(temp_dir, "test_file.txt")
with open(temp_file_path, 'w') as f:
    f.write("test content for shasum")

ARGS = {
    "file_path": temp_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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_algo_class Not yet run
unverified (harvested, no recorded run)
HarryLui98/DMPEL/libero/lifelong/algos/base.py
code served (permissive licence) · get_code("c16ef32ab232d921")
How it ran

no invocation recorded.

get_policy_class Not yet run
unverified (harvested, no recorded run)
lifelong-robot-learning/libero/libero/lifelong/models/base_policy.py
code served (permissive licence) · get_code("9c401a441a11d489")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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, 1 later) and 5 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
project 11 other papers
4 dated earlier, 6 later, 1 same year, order not determinable
2010.05595 (2020-10)
Rethinking Experience Replay: a Bag of Tricks for Continual Learning
2206.04016 (2022-06)
SYNERgy between SYNaptic consolidation and Experience Replay for general continual learning
aaai_26161 (2023 (year only))
Sparse Coding in a Dual Memory System for Lifelong Learning
and 8 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

Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of declarative knowledge of entities and concepts, lifelong learning in decision-making (LLDM) also necessitates the transfer of procedural knowledge, such as actions and behaviors. To advance research in LLDM, we introduce LIBERO, a novel benchmark of lifelong learning for robot manipulation. Specifically, LIBERO highlights five key research topics in LLDM: 1) how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both; 2) how to design effective policy architectures and 3) effective algorithms for LLDM; 4) the robustness of a lifelong learner with respect to task ordering; and 5) the effect of model pretraining for LLDM. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks. For benchmarking purpose, we create four task suites (130 tasks in total) that we use to investigate the above-mentioned research topics. To support sample-efficient learning, we provide high-quality human-teleoperated demonstration data for all tasks. Our extensive experiments present several insightful or even unexpected discoveries: sequential finetuning outperforms existing lifelong learning methods in forward transfer, no single visual encoder architecture excels at all types of knowledge transfer, and naive supervised pretraining can hinder agents' performance in the subsequent LLDM. Check the website at https://libero-project.github.io for the code and the datasets.

For agents

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

get_harvested_code_for_paper("2306.03310")
get_code_for_paper("2306.03310")
have("2306.03310")

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

curl https://syntology.ai/api/ran/2306.03310.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.03310.svg)](https://syntology.ai/paper/2306.03310)

Connect an agent — have() is free.