metadata
library_name: hivex
original_train_name: WildfireResourceManagement_difficulty_4_task_2_run_id_0_train
tags:
- hivex
- hivex-wildfire-resource-management
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-WRM-PPO-baseline-task-2-difficulty-4
results:
- task:
type: sub-task
name: distribute_all
task-id: 2
difficulty-id: 4
dataset:
name: hivex-wildfire-resource-management
type: hivex-wildfire-resource-management
metrics:
- type: cumulative_reward
value: 1093.1187683105468 +/- 578.7491242760859
name: Cumulative Reward
verified: true
- type: collective_performance
value: 71.27123718261718 +/- 32.09683856042925
name: Collective Performance
verified: true
- type: individual_performance
value: 35.614274978637695 +/- 15.634065158512929
name: Individual Performance
verified: true
- type: reward_for_moving_resources_to_neighbours
value: 914.6083679199219 +/- 397.64001336221355
name: Reward for Moving Resources to Neighbours
verified: true
- type: reward_for_moving_resources_to_self
value: 0.5484737113118172 +/- 0.339556676622338
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 2 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 2
Difficulty: 4
Algorithm: PPO
Episode Length: 500
Training max_steps: 450000
Testing max_steps: 45000
Train & Test Scripts
Download the Environment