A2C Agent playing PandaReachDense-v3
This is a trained model of an A2C agent playing PandaReachDense-v3 using the panda-gym robotic environment for Unit 6 of the Hugging Face Deep Reinforcement Learning Course.
Evaluation Results
- Mean Reward: -0.22 +/- 0.10
- Threshold Required: >= -3.5
- Pass Status: Passed ✅
- Downloads last month
- 4
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-0.22 +/- 0.10