README.md

metadata

tags:
  - ML-Agents-SnowballTarget
  - SnowballTarget
  - ml-agents
  - deep-rl-course
  - ppo
  - reinforcement-learning
library_name: ml-agents
pipeline_tag: reinforcement-learning
model-index:
  - name: ppo-SnowballTarget
    results:
      - task:
          name: reinforcement-learning
          type: reinforcement-learning
        dataset:
          name: ML-Agents-SnowballTarget
          type: ML-Agents-SnowballTarget
        metrics:
          - name: mean_reward
            type: mean_reward
            value: 18.5

PPO Agent playing SnowballTarget in Unity ML-Agents

This is a trained model of a PPO agent playing ML-Agents-SnowballTarget using Unity ML-Agents.

• Mean Reward: 18.5 +/- 1.2
• Result (mean - std): 17.30