# Locomotion on Ant Source: [Locomotion on Ant]() Collection index: [llms.txt]() Data updated: 2026-06-11T10:50:41.814Z Evaluation of locomotion performance in the Ant continuous control environment, typically measured by cumulative reward. 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 | Locomotion | | Dataset (including any stated split) | Ant | | Metric | Reward | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Reward](): Higher is better; unit: SCALAR. ## Recorded results | Method | Reward | Result date | Report paper | | --- | --- | --- | --- | | PAWS (MLP) | 882 | Not recorded | 6a2a410ed33dfb23e78392e8 | | PAWS (Trans.) | 850 | Not recorded | 6a2a410ed33dfb23e78392e8 | | P-IQL | 847 | Not recorded | 6a2a410ed33dfb23e78392e8 | | Pref Trans. | 784 | Not recorded | 6a2a410ed33dfb23e78392e8 | | PAWS (MLP) | 707 | Not recorded | 6a2a410ed33dfb23e78392e8 | | PAWS (Trans.) | 685 | Not recorded | 6a2a410ed33dfb23e78392e8 | | IPL | 634 | Not recorded | 6a2a410ed33dfb23e78392e8 | | BC | 593 | Not recorded | 6a2a410ed33dfb23e78392e8 | | CPL+KL | 581 | Not recorded | 6a2a410ed33dfb23e78392e8 | | P-IQL | 567 | Not recorded | 6a2a410ed33dfb23e78392e8 | | CPL | 563 | Not recorded | 6a2a410ed33dfb23e78392e8 | | BC | 546 | Not recorded | 6a2a410ed33dfb23e78392e8 | | CPL+KL | 518 | Not recorded | 6a2a410ed33dfb23e78392e8 | | CPL | 508 | Not recorded | 6a2a410ed33dfb23e78392e8 | | Pref Trans. | 505 | Not recorded | 6a2a410ed33dfb23e78392e8 | | IPL | 384 | Not recorded | 6a2a410ed33dfb23e78392e8 | ### PAWS (MLP) Reward: 882. Result ID: 6a2a92eafbc373592c289337. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### PAWS (Trans.) Reward: 850. Result ID: 6a2a92eafbc373592c289335. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### P-IQL Reward: 847. Result ID: 6a2a92eafbc373592c28932b. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### Pref Trans. Reward: 784. Result ID: 6a2a92eafbc373592c289331. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### PAWS (MLP) Reward: 707. Result ID: 6a2a92eafbc373592c289336. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. ### PAWS (Trans.) Reward: 685. Result ID: 6a2a92eafbc373592c289334. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. ### IPL Reward: 634. Result ID: 6a2a92eafbc373592c289333. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### BC Reward: 593. Result ID: 6a2a92eafbc373592c289329. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### CPL+KL Reward: 581. Result ID: 6a2a92eafbc373592c28932f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### P-IQL Reward: 567. Result ID: 6a2a92eafbc373592c28932a. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. ### CPL Reward: 563. Result ID: 6a2a92eafbc373592c28932d. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"500"}. This record does not assert independent reproduction. ### BC Reward: 546. Result ID: 6a2a92eafbc373592c289328. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. ### CPL+KL Reward: 518. Result ID: 6a2a92eafbc373592c28932e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. ### CPL Reward: 508. Result ID: 6a2a92eafbc373592c28932c. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. ### Pref Trans. Reward: 505. Result ID: 6a2a92eafbc373592c289330. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. ### IPL Reward: 384. Result ID: 6a2a92eafbc373592c289332. [Reporting paper]() Recorded evaluation configuration: {"#Preferences":"50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.