SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.09598 · NeurIPS · 2022

Planning for Sample Efficient Imitation Learning

Qifeng Chen, Yang Gao, Weirui Ye, Zhao-Heng Yin

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2210.09598.json · badge: /api/ran/2210.09598.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
zhaohengyin/EfficientImitate marked official in Papers with Code
Papers with Code archive
8 ran · 2 no recorded run
FunctionStatusWhere it lives
ActorCriticNetwork Ran
ran on a synthesized input · constructed an object; no result was computed
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("89159fd394eef8da")
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, ActorCriticNetwork: 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

torch.manual_seed(0)

# Define ARGS dict with all parameters for ActorCriticNetwork
ARGS = {
    'f_dim': 4,           # input feature dimension
    'out_dim': 3,         # output dimension
    'layers': [8, 6]      # hidden layer sizes
}
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 ActorCriticNetwork — 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 ActorCriticNetwork 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
PredNetwork Ran
ran on a synthesized input · constructed an object; no result was computed
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("d69e09cf8b1b9c27")
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, PredNetwork: 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

torch.manual_seed(0)

# PredNetwork.__init__ parameters:
# - h_dim: hidden dimension
# - a_dim: action dimension
# - momentum: momentum parameter (default 0.1)

h_dim = 4
a_dim = 3
momentum = 0.1

ARGS = {
    'h_dim': h_dim,
    'a_dim': a_dim,
    'momentum': momentum,
}
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 PredNetwork — 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 PredNetwork 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
RepresentationNetwork Ran
ran on a synthesized input · constructed an object; no result was computed
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("09ca94f5f2b3ffda")
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, RepresentationNetwork: 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

torch.manual_seed(0)

ARGS = {
    "observation_shape": (3, 48, 48),
    "stacked_observations": 1,
    "momentum": 0.1,
    "f_dim": 128,
}
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 RepresentationNetwork — 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 RepresentationNetwork 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
RewardNetwork Ran
ran on a synthesized input · constructed an object; no result was computed
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("cacbaaa63c29f934")
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, RewardNetwork: 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

torch.manual_seed(0)

ARGS = {
    "f_dim": 4,
    "a_dim": 3,
    "layers": [8, 6]
}
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 RewardNetwork — 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 RewardNetwork 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
dict_to_cpu Ran
ran; our contract draft was wrong, not the code
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("88b04eafd87435f2")
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

torch.manual_seed(0)

# The function dict_to_cpu takes a dictionary as input
# It recursively processes dictionaries and moves tensors to CPU
# We need to construct a test dictionary with various types of values

ARGS = {
    "dictionary": {
        "tensor_1": torch.randn(2, 4),
        "tensor_2": torch.randn(3, 5),
        "scalar": 42,
        "string": "test",
        "list": [1, 2, 3],
        "nested_dict": {
            "inner_tensor": torch.randn(4, 6),
            "inner_value": 3.14,
            "deep_nested": {
                "deep_tensor": torch.randn(2, 7),
                "deep_value": "nested"
            }
        }
    }
}
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
mlp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("4c8aa25db20d758e")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    "input_size": 4,
    "layer_sizes": [8, 6],
    "output_size": 2,
    "output_activation": nn.Identity,
    "momentum": 0.1,
    "activation": nn.ELU,
    "use_bn": True,
    "init_zero": False,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
support_to_scalar Ran
ran; our contract draft was wrong, not the code
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("8a376431bfa31f3a")
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 2, dtype family float, shape (2, 1) 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 small logits tensor: batch_size=2, num_classes=5
# The function expects logits and will apply softmax along dim=1
logits = torch.randn(2, 5)

# support_size determines the range of support values
support_size = 2

# step_size scales the support values
step_size = 1.0

ARGS = {
    "logits": logits,
    "support_size": support_size,
    "step_size": step_size,
}
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 2, dtype family float, shape (2, 1) — shape (2, 1) 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
tensor_to_numpy Ran
ran, honoured the contract we drafted
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("255167c323c80d7b")
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 ndarray, ndim 2, dtype family float, shape (2, 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 numpy as np

torch.manual_seed(0)

# Create a small tensor on CPU
tensor = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "tensor": tensor
}
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 ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
AbstractNetwork Not yet run
unverified (harvested, no recorded run)
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("a2ab73a0251612a4")
How it ran

no invocation recorded.

MuZeroResidualNetwork Not yet run
unverified (harvested, no recorded run)
zhaohengyin/EfficientImitate/algo/obs_ei/model.py
code served (permissive licence) · get_code("184612793da7dac1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 9 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
dict_to_cpu
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2111.00210 (2021-11)
Mastering Atari Games with Limited Data
2602.12162 (2026-02)
Amortized Molecular Optimization via Group Relative Policy Optimization

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

Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the exploration hardness. However, the current imitation algorithm struggles to achieve both high performance and high in-environment sample efficiency simultaneously. Behavioral Cloning (BC) does not need in-environment interactions, but it suffers from the covariate shift problem which harms its performance. Adversarial Imitation Learning (AIL) turns imitation learning into a distribution matching problem. It can achieve better performance on some tasks but it requires a large number of in-environment interactions. Inspired by the recent success of EfficientZero in RL, we propose EfficientImitate (EI), a planning-based imitation learning method that can achieve high in-environment sample efficiency and performance simultaneously. Our algorithmic contribution in this paper is two-fold. First, we extend AIL into the MCTS-based RL. Second, we show the seemingly incompatible two classes of imitation algorithms (BC and AIL) can be naturally unified under our framework, enjoying the benefits of both. We benchmark our method not only on the state-based DeepMind Control Suite, but also on the image version which many previous works find highly challenging. Experimental results show that EI achieves state-of-the-art results in performance and sample efficiency. EI shows over 4x gain in performance in the limited sample setting on state-based and image-based tasks and can solve challenging problems like Humanoid, where previous methods fail with small amount of interactions. Our code is available at https://github.com/zhaohengyin/EfficientImitate.

For agents

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

get_harvested_code_for_paper("2210.09598")
get_code_for_paper("2210.09598")
have("2210.09598")

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

curl https://syntology.ai/api/ran/2210.09598.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.09598.svg)](https://syntology.ai/paper/2210.09598)

Connect an agent — have() is free.