# Multi-Agent Reinforcement Learning (Predator-Prey) on MPE PP\_9/3 Source: [Multi-Agent Reinforcement Learning (Predator-Prey) on MPE PP\_9/3]() Collection index: [llms.txt]() Data updated: 2026-05-21T10:05:33.957Z Evaluation of Multi-Agent Reinforcement Learning performance on the MPE Predator-Prey environment configuration PP\_9/3, 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\_9/3 | | 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 | 802.5 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 802.5 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 721.4 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 701.7 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 698.1 | Not recorded | 68fa797b1e209131cea7dbe7 | | WALL | 682.7 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 666.9 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 661.9 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 657.9 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 656.4 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 624.3 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 594.4 | Not recorded | 68fa797b1e209131cea7dbe7 | | RANDOM | 589.7 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 585.1 | Not recorded | 68fa797b1e209131cea7dbe7 | | ROMANCE | 570.3 | Not recorded | 68fa797b1e209131cea7dbe7 | | Vanilla QMIX | 551.7 | Not recorded | 68fa797b1e209131cea7dbe7 | ### WALL Average Cumulative Reward: 802.5. Result ID: 6a0ed8d9fbc373592c069cad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 802.5. Result ID: 6a0ed8d9fbc373592c069cb1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 721.4. Result ID: 6a0ed8d9fbc373592c069cac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 701.7. Result ID: 6a0ed8d9fbc373592c069cb0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 698.1. Result ID: 6a0ed8d9fbc373592c069cb9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. ### WALL Average Cumulative Reward: 682.7. Result ID: 6a0ed8d9fbc373592c069cb5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 666.9. Result ID: 6a0ed8d9fbc373592c069cab. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 661.9. Result ID: 6a0ed8d9fbc373592c069caa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"Natural"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 657.9. Result ID: 6a0ed8d9fbc373592c069caf. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 656.4. Result ID: 6a0ed8d9fbc373592c069cae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"Radom Attack"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 624.3. Result ID: 6a0ed8d9fbc373592c069cb7. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"Wolfpack Adversarial Attack"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 594.4. Result ID: 6a0ed8d9fbc373592c069cb4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### RANDOM Average Cumulative Reward: 589.7. Result ID: 6a0ed8d9fbc373592c069cb3. [Reporting paper]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### Vanilla QMIX Average Cumulative Reward: 585.1. Result ID: 6a0ed8d9fbc373592c069cb2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack Method":"EGA"}. This record does not assert independent reproduction. ### ROMANCE Average Cumulative Reward: 570.3. Result ID: 6a0ed8d9fbc373592c069cb8. [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: 551.7. Result ID: 6a0ed8d9fbc373592c069cb6. [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.