metadata
library_name: hivex
original_train_name: OceanPlasticCollection_task_1_run_id_0_train
tags:
- hivex
- hivex-ocean-plastic-collection
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-OPC-PPO-baseline-task-1
results:
- task:
type: sub-task
name: find_highest_polluted_area
task-id: 1
dataset:
name: hivex-ocean-plastic-collection
type: hivex-ocean-plastic-collection
metrics:
- type: cumulative_reward
value: 994.6653747558594 +/- 158.13702190020126
name: Cumulative Reward
verified: true
- type: global_reward
value: 226.50474700927734 +/- 57.553598550844015
name: Global Reward
verified: true
- type: local_reward
value: 142.19907608032227 +/- 19.368785745326573
name: Local Reward
verified: true
This model serves as the baseline for the Ocean Plastic Collection environment, trained and tested on task 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Ocean Plastic Collection
Task: 1
Algorithm: PPO
Episode Length: 5000
Training max_steps: 3000000
Testing max_steps: 150000
Train & Test Scripts
Download the Environment