{"h_size": 512, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.05, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3} |
{"h_size": 512, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.05, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3} |