{"h_size": [21, 49, 9], "n_training_episodes": 100000, "n_evaluation_episodes": 1000, "max_t": 10000, "gamma": 0.999, "lr": 0.003, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3} |
{"h_size": [21, 49, 9], "n_training_episodes": 100000, "n_evaluation_episodes": 1000, "max_t": 10000, "gamma": 0.999, "lr": 0.003, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3} |