metadata
library_name: hivex
original_train_name: WildfireResourceManagement_difficulty_5_task_1_run_id_1_train
tags:
- hivex
- hivex-wildfire-resource-management
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-WRM-PPO-baseline-task-1-difficulty-5
results:
- task:
type: sub-task
name: keep_all
task-id: 1
difficulty-id: 5
dataset:
name: hivex-wildfire-resource-management
type: hivex-wildfire-resource-management
metrics:
- type: cumulative_reward
value: 301.4590789794922 +/- 50.589352153281204
name: Cumulative Reward
verified: true
- type: collective_performance
value: 52.42880744934082 +/- 13.213045945399395
name: Collective Performance
verified: true
- type: individual_performance
value: 27.22167682647705 +/- 6.5057905262466
name: Individual Performance
verified: true
- type: reward_for_moving_resources_to_neighbours
value: 1.2814587712287904 +/- 0.3169255575214482
name: Reward for Moving Resources to Neighbours
verified: true
- type: reward_for_moving_resources_to_self
value: 233.32887573242186 +/- 58.13535329798181
name: Reward for Moving Resources to Self
verified: true
This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 1 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 1
Difficulty: 5
Algorithm: PPO
Episode Length: 500
Training max_steps: 450000
Testing max_steps: 45000
Train & Test Scripts
Download the Environment