SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.05421 · NeurIPS · 2024

DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning

Ziyu Wang, Yufei Wang, David Held, Zackory Erickson, San Diego, Weikang Wan

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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, 3 violated it and 0 have no contract verdict; 4 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/2402.05421.json · badge: /api/ran/2402.05421.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
wkwan7/DiffTORI canonical (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
create_indices Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/sampler.py
pointer only (licence: NONE) · get_code("0a16eab1dfc7ced0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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.

dict_apply Ran
ran; our contract draft was wrong, not the code
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/pytorch_util.py
pointer only (licence: NONE) · get_code("e889bd81b4735ee5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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.

dict_apply_split Ran
ran; our contract draft was wrong, not the code
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/pytorch_util.py
pointer only (licence: NONE) · get_code("8c6a9f390c7af799")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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.

downsample_mask Ran
ran, violated the contract we drafted
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/sampler.py
pointer only (licence: NONE) · get_code("85ef80fba2caa71d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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_optimal_chunks Ran
ran; our contract draft was wrong, not the code
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/replay_buffer.py
pointer only (licence: NONE) · get_code("1d4ddad52e215d73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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_val_mask Ran
ran, violated the contract we drafted
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/sampler.py
pointer only (licence: NONE) · get_code("ed689847c85c1288")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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.

pad_remaining_dims Ran
ran, violated the contract we drafted
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/pytorch_util.py
pointer only (licence: NONE) · get_code("ad05722d0bd12d1e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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.

read_json_log Not yet run
unverified (harvested, no recorded run)
wkwan7/DiffTORI/DiffTORI_IL_Metaworld/DiffTORI/diffusion_policy_3d/common/json_logger.py
pointer only (licence: NONE) · get_code("d83f4930e9aa9202")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wkwan7/DiffTORI 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. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 8 later) and 0 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_apply 4 other papers
4 later
2403.03206 (2024-03)
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
2403.03954 (2024-03)
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
2411.02359 (2024-11)
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
and 1 more not named here
dict_apply_split 3 other papers
3 later
2403.03206 (2024-03)
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
2403.03954 (2024-03)
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
2503.07511 (2025-03)
PointVLA: Injecting the 3D World into Vision-Language-Action Models
downsample_mask 3 other papers
3 later
2403.03206 (2024-03)
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
2403.03954 (2024-03)
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
2503.07511 (2025-03)
PointVLA: Injecting the 3D World into Vision-Language-Action Models
get_optimal_chunks 3 other papers
3 later
2403.03206 (2024-03)
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
2403.03954 (2024-03)
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
2503.07511 (2025-03)
PointVLA: Injecting the 3D World into Vision-Language-Action Models
get_val_mask 3 other papers
3 later
2403.03206 (2024-03)
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
2403.03954 (2024-03)
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
2503.07511 (2025-03)
PointVLA: Injecting the 3D World into Vision-Language-Action Models
pad_remaining_dims 3 other papers
3 later
2403.03206 (2024-03)
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
2403.03954 (2024-03)
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
2503.07511 (2025-03)
PointVLA: Injecting the 3D World into Vision-Language-Action Models
read_json_log 3 other papers
3 later
2403.03206 (2024-03)
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
2406.04806 (2024-06)
Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models
2503.07511 (2025-03)
PointVLA: Injecting the 3D World into Vision-Language-Action Models
create_indices 2 other papers
2 later
2403.03954 (2024-03)
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
2503.07511 (2025-03)
PointVLA: Injecting the 3D World into Vision-Language-Action Models

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

This paper introduces DiffTORI, which utilizes Differentiable Trajectory Optimization as the policy representation to generate actions for deep Reinforcement and Imitation learning. Trajectory optimization is a powerful and widely used algorithm in control, parameterized by a cost and a dynamics function. The key to our approach is to leverage the recent progress in differentiable trajectory optimization, which enables computing the gradients of the loss with respect to the parameters of trajectory optimization. As a result, the cost and dynamics functions of trajectory optimization can be learned end-to-end. DiffTORI addresses the "objective mismatch" issue of prior model-based RL algorithms, as the dynamics model in DiffTORI is learned to directly maximize task performance by differentiating the policy gradient loss through the trajectory optimization process. We further benchmark DiffTORI for imitation learning on standard robotic manipulation task suites with high-dimensional sensory observations and compare our method to feed-forward policy classes as well as Energy-Based Models (EBM) and Diffusion. Across 15 model-based RL tasks and 35 imitation learning tasks with high-dimensional image and point cloud inputs, DiffTORI outperforms prior state-of-the-art methods in both domains. Our code is available at https://github.com/wkwan7/DiffTORI. * Equal contribution. This work was performed when Weikang Wan and Ziyu Wang were interning at CMU. † Equal Advising. Differentiable optimization and implicit policy representation: Our work follows the line of research on differentiable optimization, which embeds optimization problems as a layer in neural networks for end-to-end learning. Early works focus on differentiating through convex optimization problems [23; 24]. Recent works extend the range of optimization problems that can be made differentiable [11; 12; 6; 8; 9; 10]. The mostly related prior work to ours are Amos et al. [3] and Jin et al. [6], which first proposed to treat trajectory optimization as an implicit policy and demonstrated its effectiveness in the setting of behavior cloning, system identification, and control for robotics problems with low-dimensional states. Another closely related recent work is Romero et

For agents

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

get_harvested_code_for_paper("2402.05421")
get_code_for_paper("2402.05421")
have("2402.05421")

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

curl https://syntology.ai/api/ran/2402.05421.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.05421.svg)](https://syntology.ai/paper/2402.05421)

Connect an agent — have() is free.