A2C Agent playing PandaReachDense-v3
This is a trained A2C model playing PandaReachDense-v3 using the stable-baselines3 library. Trained by keeerthinakka for the Hugging Face Deep Reinforcement Learning Course.
- Downloads last month
- 4
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-1.20 +/- 0.10