# Multi-Agent Reinforcement Learning on MPE PP\_3/1 Source: [Multi-Agent Reinforcement Learning on MPE PP\_3/1]() Collection index: [llms.txt]() Data updated: 2026-05-21T10:05:33.881Z Evaluation of Multi-Agent Reinforcement Learning performance on the MPE Predator-Prey environment configuration PP\_3/1, 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\_3/1 | | 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 | 202.9 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 202.9 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 178.3 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 175 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 173.4 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 171.5 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 170.1 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 167.1 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 166.5 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 165.4 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 159.3 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 158.9 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 157.6 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 157.5 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 153.7 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 135.7 | Not recorded | 68fa797b1e209131cea7dbe7 | ### WALL Average Cumulative Reward: 202.9. Result ID: 6a0ed8d9fbc373592c069c8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 202.9. Result ID: 6a0ed8d9fbc373592c069c91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 178.3. Result ID: 6a0ed8d9fbc373592c069c8b. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 175. Result ID: 6a0ed8d9fbc373592c069c8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 173.4. Result ID: 6a0ed8d9fbc373592c069c90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 171.5. Result ID: 6a0ed8d9fbc373592c069c99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 170.1. Result ID: 6a0ed8d9fbc373592c069c8f. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 167.1. Result ID: 6a0ed8d9fbc373592c069c94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 166.5. Result ID: 6a0ed8d9fbc373592c069c95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 165.4. Result ID: 6a0ed8d9fbc373592c069c8a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 159.3. Result ID: 6a0ed8d9fbc373592c069c98. [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: 158.9. Result ID: 6a0ed8d9fbc373592c069c8e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 157.6. Result ID: 6a0ed8d9fbc373592c069c93. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 157.5. Result ID: 6a0ed8d9fbc373592c069c97. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 153.7. Result ID: 6a0ed8d9fbc373592c069c92. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 135.7. Result ID: 6a0ed8d9fbc373592c069c96. [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.