| {"experiment_name": "Reinforce_Pixelcopter-PLE-v0", "device": "gpu", "policy": {"_target_": "lib.reinforce.Policy", "h_size": 64, "n_layers": 3}, "optimizer": {"_target_": "torch.optim.Adam", "lr": 0.0001}, "train_hparams": {"n_training_episodes": 100000, "max_steps": 10000, "gamma": 0.99, "print_every": 100}, "eval_hparams": {"n_eval_episodes": 10, "max_steps": 10000}, "model_path": "model.pt", "hparams_path": "hyperparameters.json", "video_path": "replay.mp4", "video_fps": 30, "train_env": {"_target_": "gym.make", "id": "Pixelcopter-PLE-v0"}, "eval_env": {"_target_": "gym.make", "id": "Pixelcopter-PLE-v0"}} |