PPO Agent playing ML-Agents-SnowballTarget

This is a trained model of a PPO agent playing ML-Agents-SnowballTarget using the ml-agents library. This model was trained for Unit 5 (Part 1) of the Deep Reinforcement Learning Course.

Usage

Trained Unity ML-Agents agent on SnowballTarget for Unit 5 of the Deep RL Course.

Evaluation Results

• Mean Reward: 35.00 +/- 2.50
• Environment: ML-Agents-SnowballTarget
• Algorithm: PPO