REINFORCE Agent playing Pixelcopter-PLE-v0
This is a trained model of a REINFORCE agent playing Pixelcopter-PLE-v0 using the Deep Reinforcement Learning Course.
Usage
model = PixelcopterPolicy(7, 2, 64)
model.load_state_dict(torch.load("model.pt"))
Evaluation results
- mean_reward on Pixelcopter-PLE-v0self-reported10.70 +/- 0.46