# Trajectory Distribution Matching on Two-Agent Swap Robosuite simulation (100 sampled trajectories)

Source: [Trajectory Distribution Matching on Two-Agent Swap Robosuite simulation (100 sampled trajectories)](<https://www.sota2.com/research/sota/trajectory-distribution-matching-on-two-agent-swap-robosuite-simulation-100-sampled-trajectories>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:41:44.501Z

Evaluation of trajectory distribution matching performance using Earth Mover's Distance (EMD) metrics for both agents within the Two-Agent Swap Robosuite simulation environment, based on 100 sampled trajectories.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Trajectory Distribution Matching |
| Dataset (including any stated split) | Two-Agent Swap Robosuite simulation (100 sampled trajectories) |
| Metric | EMD (Agent 1) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [EMD (Agent 1)](<https://www.sota2.com/research/sota/trajectory-distribution-matching-on-two-agent-swap-robosuite-simulation-100-sampled-trajectories.md?metric=EMD%20(Agent%201)>): Lower is better; unit: SCALAR.

- [EMD (Agent 2)](<https://www.sota2.com/research/sota/trajectory-distribution-matching-on-two-agent-swap-robosuite-simulation-100-sampled-trajectories.md?metric=EMD%20(Agent%202)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | EMD (Agent 1) | Result date | Report paper |
| --- | --- | --- | --- |
| Vanilla CTDE Diffusion | 1.2 | Not recorded | 68fa7b6c1e209131cea885b6 |
| MIMIC-D | 1.5 | Not recorded | 68fa7b6c1e209131cea885b6 |
| BC | 1.93 | Not recorded | 68fa7b6c1e209131cea885b6 |
| MAGAIL | 4.67 | Not recorded | 68fa7b6c1e209131cea885b6 |

### Vanilla CTDE Diffusion

EMD (Agent 1): 1.2. Result ID: 699d00bf5698665ec4a0dad9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885b6.md>)

Recorded evaluation configuration: {"Nature":"stochastic"}. This record does not assert independent reproduction.

### MIMIC-D

EMD (Agent 1): 1.5. Result ID: 699d00bf5698665ec4a0dada.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885b6.md>)

Recorded evaluation configuration: {"Nature":"stochastic"}. This record does not assert independent reproduction.

### BC

EMD (Agent 1): 1.93. Result ID: 699d00bf5698665ec4a0dad7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885b6.md>)

Recorded evaluation configuration: {"Nature":"deterministic"}. This record does not assert independent reproduction.

### MAGAIL

EMD (Agent 1): 4.67. Result ID: 699d00bf5698665ec4a0dad8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885b6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea05882.md>)

Recorded evaluation configuration: {"Nature":"deterministic"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.