swaroop06
/

ppo-SnowballTarget

Reinforcement Learning

ML-Agents-SnowballTarget

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

PPO agent playing ML-Agents-SnowballTarget

This is a trained model of an PPO agent playing ML-Agents-SnowballTarget for the Hugging Face Deep Reinforcement Learning Course (Unit 5 P1).

Evaluation Results

Mean Reward: 42.00 +/- 5.00
Environment: ML-Agents-SnowballTarget
Algorithm: PPO
Library: ml-agents

Usage

Trained and evaluated for the Hugging Face Deep RL Course certification.

Downloads last month: 14

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on ML-Agents-SnowballTarget
self-reported

42.00 +/- 5.00