---
library_name: hivex
original_train_name: OceanPlasticCollection_task_0_run_id_0_train
tags:
- hivex
- hivex-ocean-plastic-collection
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-OPC-PPO-baseline-task-0
  results:
  - task:
      type: main-task
      name: main_task
      task-id: 0
    dataset:
      name: hivex-ocean-plastic-collection
      type: hivex-ocean-plastic-collection
    metrics:
    - type: cumulative_reward
      value: 823.2983947753906 +/- 197.42713024318527
      name: "Cumulative Reward"
      verified: true
    - type: global_reward
      value: 285.8913818359375 +/- 84.43798423128938
      name: "Global Reward"
      verified: true
    - type: local_reward
      value: 158.69510040283203 +/- 32.16273712262643
      name: "Local Reward"
      verified: true
---

This model serves as the baseline for the **Ocean Plastic Collection** environment, trained and tested on task <code>0</code> using the Proximal Policy Optimization (PPO) algorithm.<br>
<br>
Environment: **Ocean Plastic Collection**<br>
Task: <code>0</code><br>
Algorithm: <code>PPO</code><br>
Episode Length: <code>5000</code><br>
Training <code>max_steps</code>: <code>3000000</code><br>
Testing <code>max_steps</code>: <code>150000</code><br>
<br>
Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
Download the [Environment](https://github.com/hivex-research/hivex-environments)

[hivex-paper]: https://arxiv.org/abs/2501.04180