a2c-PandaReachDense-v3 Agent playing PandaReachDense-v3
This is a trained model of a a2c-PandaReachDense-v3 agent playing PandaReachDense-v3 using the stable-baselines3 library. Trained for the Hugging Face Deep Reinforcement Learning Course.
Evaluation Results
- Mean Reward: -0.24
- Std Reward: 0.14
- Score (Mean - Std): -0.38
- Downloads last month
- 3
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-0.24 +/- 0.14