metadata
library_name: hivex
original_train_name: OceanPlasticCollection_task_2_run_id_1_train
tags:
- hivex
- hivex-ocean-plastic-collection
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-OPC-PPO-baseline-task-2
results:
- task:
type: sub-task
name: group_up
task-id: 2
dataset:
name: hivex-ocean-plastic-collection
type: hivex-ocean-plastic-collection
metrics:
- type: cumulative_reward
value: 868.6791931152344 +/- 177.8582676854445
name: Cumulative Reward
verified: true
- type: global_reward
value: 294.7176452636719 +/- 58.7408861442478
name: Global Reward
verified: true
- type: local_reward
value: 165.2141372680664 +/- 20.43658256777414
name: Local Reward
verified: true
This model serves as the baseline for the Ocean Plastic Collection environment, trained and tested on task 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Ocean Plastic Collection
Task: 2
Algorithm: PPO
Episode Length: 5000
Training max_steps: 3000000
Testing max_steps: 150000
Train & Test Scripts
Download the Environment