# Multi-Agent Reinforcement Learning (Predator-Prey) on MPE PP\_6/2 Source: [Multi-Agent Reinforcement Learning (Predator-Prey) on MPE PP\_6/2]() Collection index: [llms.txt]() Data updated: 2026-05-21T10:05:33.923Z Evaluation of Multi-Agent Reinforcement Learning performance on the MPE Predator-Prey environment using the PP\_6/2 configuration, measured by Average 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 | Multi-Agent Reinforcement Learning (Predator-Prey) | | Dataset (including any stated split) | MPE PP\_6/2 | | Metric | Average Cumulative 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 - [Average Cumulative Reward](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Cumulative Reward | Result date | Report paper | | --- | --- | --- | --- | | WALL | 685.5 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 675 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 663.8 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 654 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 648.6 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 638.7 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 624.2 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 605.1 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 604.6 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 599 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 571 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 554.6 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 538.8 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 522.6 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 499.8 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 415.6 | Not recorded | 68fa797b1e209131cea7dbe7 | ### WALL Average Cumulative Reward: 685.5. Result ID: 6a0ed8d9fbc373592c069ca5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 675. Result ID: 6a0ed8d9fbc373592c069c9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 663.8. Result ID: 6a0ed8d9fbc373592c069c9b. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 654. Result ID: 6a0ed8d9fbc373592c069ca1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 648.6. Result ID: 6a0ed8d9fbc373592c069c9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 638.7. Result ID: 6a0ed8d9fbc373592c069c9f. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 624.2. Result ID: 6a0ed8d9fbc373592c069ca0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 605.1. Result ID: 6a0ed8d9fbc373592c069ca4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 604.6. Result ID: 6a0ed8d9fbc373592c069ca3. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 599. Result ID: 6a0ed8d9fbc373592c069ca9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 571. Result ID: 6a0ed8d9fbc373592c069ca7. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 554.6. Result ID: 6a0ed8d9fbc373592c069ca8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 538.8. Result ID: 6a0ed8d9fbc373592c069c9a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 522.6. Result ID: 6a0ed8d9fbc373592c069c9e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 499.8. Result ID: 6a0ed8d9fbc373592c069ca2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 415.6. Result ID: 6a0ed8d9fbc373592c069ca6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.