ppo-SnowballTarget
This is a trained model of a Reinforcement Learning agent for ML-Agents-SnowballTarget using ml-agents. Created for the Hugging Face Deep RL Course.
Evaluation Results
- Mean Reward: 20.00 +/- 5.00
- Target Environment:
ML-Agents-SnowballTarget - Library:
ml-agents - Model Architecture:
PPO (ML-Agents)
- Downloads last month
- 9
Evaluation results
- reward on ML-Agents-SnowballTargetself-reported20.00 +/- 5.00