Hugging Peers

ppo-Huggy

☆ Save
by swaroop06 reinforcement-learning ml-agents
54 downloads 0 likes on Hugging Face updated

Model card

PPO agent playing Huggy

This is a trained model of an PPO agent playing Huggy for the Hugging Face Deep Reinforcement Learning Course (Bonus Unit 1).

Evaluation Results

  • Mean Reward: 15.00 +/- 1.50
  • Environment: Huggy
  • Algorithm: PPO
  • Library: ml-agents

Usage

Trained and evaluated for the Hugging Face Deep RL Course.