# Reinforcement Learning on Task Average HC, Ant, Hop, Walk v5 Source: [Reinforcement Learning on Task Average HC, Ant, Hop, Walk v5]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:22:44.785Z Evaluation of Reinforcement Learning performance averaged across the HC, Ant, Hop, and Walk environments, all using version 5 specifications. 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 | Reinforcement Learning | | Dataset (including any stated split) | Task Average HC, Ant, Hop, Walk v5 | | Metric | Mean Episodic Return | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Mean Episodic Return](): Higher is better; unit: SCALAR. ## Recorded results | Method | Mean Episodic Return | Result date | Report paper | | --- | --- | --- | --- | | SAID | 7282 | Not recorded | 69a66c622d603e6de3e3d20c | | SAC | 6067 | Not recorded | 69a66c622d603e6de3e3d20c | | SAID | 5452 | Not recorded | 69a66c622d603e6de3e3d20c | | SADR | 5078 | Not recorded | 69a66c622d603e6de3e3d20c | | SAID | 4478 | Not recorded | 69a66c622d603e6de3e3d20c | | VDPO | 4425 | Not recorded | 69a66c622d603e6de3e3d20c | | SAID | 4402 | Not recorded | 69a66c622d603e6de3e3d20c | | SADR | 4140 | Not recorded | 69a66c622d603e6de3e3d20c | | SADR | 3920 | Not recorded | 69a66c622d603e6de3e3d20c | | VDPO | 3056 | Not recorded | 69a66c622d603e6de3e3d20c | | VDPO | 2314 | Not recorded | 69a66c622d603e6de3e3d20c | | DR | 2247 | Not recorded | 69a66c622d603e6de3e3d20c | | DR | 1652 | Not recorded | 69a66c622d603e6de3e3d20c | | DR | 753 | Not recorded | 69a66c622d603e6de3e3d20c | | SAC | 366 | Not recorded | 69a66c622d603e6de3e3d20c | | SAC | 275 | Not recorded | 69a66c622d603e6de3e3d20c | | SAC | 262 | Not recorded | 69a66c622d603e6de3e3d20c | ### SAID Mean Episodic Return: 7282. Result ID: 69a840326dbb7075b94f052f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Delay steps":"0"}. This record does not assert independent reproduction. ### SAC Mean Episodic Return: 6067. Result ID: 69a840326dbb7075b94f0522. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Delay steps":"0"}. This record does not assert independent reproduction. ### SAID Mean Episodic Return: 5452. Result ID: 69a840326dbb7075b94f0530. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction. ### SADR Mean Episodic Return: 5078. Result ID: 69a840326dbb7075b94f0529. [Reporting paper]() Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction. ### SAID Mean Episodic Return: 4478. Result ID: 69a840326dbb7075b94f0531. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction. ### VDPO Mean Episodic Return: 4425. Result ID: 69a840326dbb7075b94f052c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction. ### SAID Mean Episodic Return: 4402. Result ID: 69a840326dbb7075b94f0532. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction. ### SADR Mean Episodic Return: 4140. Result ID: 69a840326dbb7075b94f052a. [Reporting paper]() Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction. ### SADR Mean Episodic Return: 3920. Result ID: 69a840326dbb7075b94f052b. [Reporting paper]() Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction. ### VDPO Mean Episodic Return: 3056. Result ID: 69a840326dbb7075b94f052d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction. ### VDPO Mean Episodic Return: 2314. Result ID: 69a840326dbb7075b94f052e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction. ### DR Mean Episodic Return: 2247. Result ID: 69a840326dbb7075b94f0526. [Reporting paper]() Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction. ### DR Mean Episodic Return: 1652. Result ID: 69a840326dbb7075b94f0527. [Reporting paper]() Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction. ### DR Mean Episodic Return: 753. Result ID: 69a840326dbb7075b94f0528. [Reporting paper]() Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction. ### SAC Mean Episodic Return: 366. Result ID: 69a840326dbb7075b94f0523. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction. ### SAC Mean Episodic Return: 275. Result ID: 69a840326dbb7075b94f0524. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction. ### SAC Mean Episodic Return: 262. Result ID: 69a840326dbb7075b94f0525. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.