kalypso42's picture
First Push
9591122
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9677336812019348,
"min": 0.9677336812019348,
"max": 2.8608670234680176,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9250.56640625,
"min": 9250.56640625,
"max": 29298.138671875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.458965301513672,
"min": 0.3467920422554016,
"max": 12.458965301513672,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2429.498291015625,
"min": 67.27765655517578,
"max": 2504.470458984375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06585858188291062,
"min": 0.06260083079225083,
"max": 0.07390293292196208,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2634343275316425,
"min": 0.2589429729268886,
"max": 0.3695146646098104,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2045800569010716,
"min": 0.1191582498049327,
"max": 0.2649978983051636,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8183202276042864,
"min": 0.4766329992197308,
"max": 1.3249894915258182,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.0,
"min": 3.3181818181818183,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 146.0,
"max": 1332.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.3181818181818183,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 146.0,
"max": 1332.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1700222646",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700223144"
},
"total": 498.84990184500003,
"count": 1,
"self": 0.4381009150001205,
"children": {
"run_training.setup": {
"total": 0.044233740999970905,
"count": 1,
"self": 0.044233740999970905
},
"TrainerController.start_learning": {
"total": 498.36756718899994,
"count": 1,
"self": 0.5794089149991919,
"children": {
"TrainerController._reset_env": {
"total": 8.435459654999988,
"count": 1,
"self": 8.435459654999988
},
"TrainerController.advance": {
"total": 489.2622205880008,
"count": 18200,
"self": 0.276508394001155,
"children": {
"env_step": {
"total": 488.98571219399963,
"count": 18200,
"self": 337.59713320601577,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.09257301898674,
"count": 18200,
"self": 1.585444413997152,
"children": {
"TorchPolicy.evaluate": {
"total": 149.5071286049896,
"count": 18200,
"self": 149.5071286049896
}
}
},
"workers": {
"total": 0.2960059689971217,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 496.90294841099177,
"count": 18200,
"is_parallel": true,
"self": 240.01049076999783,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004884022999988247,
"count": 1,
"is_parallel": true,
"self": 0.0032750390000160223,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016089839999722244,
"count": 10,
"is_parallel": true,
"self": 0.0016089839999722244
}
}
},
"UnityEnvironment.step": {
"total": 0.03899858900001618,
"count": 1,
"is_parallel": true,
"self": 0.0006570570000121734,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033376099997894926,
"count": 1,
"is_parallel": true,
"self": 0.00033376099997894926
},
"communicator.exchange": {
"total": 0.03596660100004101,
"count": 1,
"is_parallel": true,
"self": 0.03596660100004101
},
"steps_from_proto": {
"total": 0.0020411699999840494,
"count": 1,
"is_parallel": true,
"self": 0.00038507999988723896,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016560900000968104,
"count": 10,
"is_parallel": true,
"self": 0.0016560900000968104
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 256.89245764099394,
"count": 18199,
"is_parallel": true,
"self": 11.047974458995668,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.725082351000651,
"count": 18199,
"is_parallel": true,
"self": 5.725082351000651
},
"communicator.exchange": {
"total": 203.15684601200002,
"count": 18199,
"is_parallel": true,
"self": 203.15684601200002
},
"steps_from_proto": {
"total": 36.9625548189976,
"count": 18199,
"is_parallel": true,
"self": 7.112817588972575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.849737230025028,
"count": 181990,
"is_parallel": true,
"self": 29.849737230025028
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000169789999972636,
"count": 1,
"self": 0.000169789999972636,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 485.1443609830747,
"count": 496217,
"is_parallel": true,
"self": 10.77295718605086,
"children": {
"process_trajectory": {
"total": 275.00496872002356,
"count": 496217,
"is_parallel": true,
"self": 273.87120231302356,
"children": {
"RLTrainer._checkpoint": {
"total": 1.133766406999996,
"count": 4,
"is_parallel": true,
"self": 1.133766406999996
}
}
},
"_update_policy": {
"total": 199.3664350770003,
"count": 90,
"is_parallel": true,
"self": 64.96658327299934,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.39985180400095,
"count": 4584,
"is_parallel": true,
"self": 134.39985180400095
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09030824100000245,
"count": 1,
"self": 0.0008990270000595046,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08940921399994295,
"count": 1,
"self": 0.08940921399994295
}
}
}
}
}
}
}