Trained PPO Agent for ML-Agents-SnowballTarget
This model is a trained PPO agent submitted for Unit 5 P1 of the Hugging Face Deep Reinforcement Learning Course.
Model Details
- User: mohanpoduri2005
- Unit: Unit 5 P1
- Environment:
ML-Agents-SnowballTarget - Library:
ml-agents - Algorithm: PPO
- Evaluation Score:
15.0 +/- 2.0 - Min Passing Result Required:
-100
Usage
This repository contains the trained model weights and evaluation metadata ready to be benchmarked and evaluated on the Deep RL Course Leaderboard.
- Downloads last month
- -
Evaluation results
- mean_reward on ML-Agents-SnowballTargetself-reported15.0 +/- 2.0