metadata
library_name: ml-agents
tags:
- SoccerTwos
- ML-Agents-SoccerTwos
- deep-rl-course
- reinforcement-learning
- reinforcement-learning-leaderboard
model-index:
- name: ppo-SoccerTwos
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: ML-Agents-SoccerTwos
type: ML-Agents-SoccerTwos
metrics:
- type: mean_reward
value: 0.7
name: mean_reward
ppo-SoccerTwos
Final surgical fix for Unit 7 Honors Certification. Multi-agent Reinforcement Learning (MARL) agent for SoccerTwos.