Trained A2C Agent for PandaReachDense-v3
This model is a trained A2C agent submitted for Unit 6 of the Hugging Face Deep Reinforcement Learning Course.
Model Details
- User: mohanpoduri2005
- Unit: Unit 6
- Environment:
PandaReachDense-v3 - Library:
stable-baselines3 - Algorithm: A2C
- Evaluation Score:
-0.15 +/- 0.05 - Min Passing Result Required:
-3.5
Usage
This repository contains the trained model weights and evaluation metadata ready to be benchmarked and evaluated on the Deep RL Course Leaderboard.
- Downloads last month
- 6
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-0.15 +/- 0.05