SnowballTarget1 / run_logs /timers.json
iblub's picture
First training
92f2e7e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7787833213806152,
"min": 0.7787833213806152,
"max": 2.8717827796936035,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7410.123046875,
"min": 7410.123046875,
"max": 29473.10546875,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.148417472839355,
"min": 0.23556305468082428,
"max": 13.148417472839355,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2550.79296875,
"min": 45.69923400878906,
"max": 2680.2080078125,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.09660800990180482,
"min": 0.09355153827598449,
"max": 0.10682350488573485,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3864320396072193,
"min": 0.38026903087858743,
"max": 0.4997285661372064,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19786892526363042,
"min": 0.09604839638895973,
"max": 0.25693897239717783,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7914757010545217,
"min": 0.38419358555583893,
"max": 1.2846948619858891,
"count": 25
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.7456980848e-06,
"min": 5.7456980848e-06,
"max": 0.00029350560216479996,
"count": 25
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.29827923392e-05,
"min": 2.29827923392e-05,
"max": 0.0014081280306239997,
"count": 25
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10191520000000003,
"min": 0.10191520000000003,
"max": 0.19783520000000002,
"count": 25
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4076608000000001,
"min": 0.4076608000000001,
"max": 0.9693759999999998,
"count": 25
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00010556848000000002,
"min": 0.00010556848000000002,
"max": 0.00489197648,
"count": 25
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004222739200000001,
"min": 0.0004222739200000001,
"max": 0.0234718624,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.90909090909091,
"min": 2.727272727272727,
"max": 25.90909090909091,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 120.0,
"max": 1410.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 2.727272727272727,
"max": 25.90909090909091,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 120.0,
"max": 1410.0,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674738888",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674739474"
},
"total": 586.0041838619999,
"count": 1,
"self": 0.38499932499996703,
"children": {
"run_training.setup": {
"total": 0.11034810599994671,
"count": 1,
"self": 0.11034810599994671
},
"TrainerController.start_learning": {
"total": 585.508836431,
"count": 1,
"self": 0.6911838860002035,
"children": {
"TrainerController._reset_env": {
"total": 10.536367842999994,
"count": 1,
"self": 10.536367842999994
},
"TrainerController.advance": {
"total": 574.1679831829999,
"count": 22739,
"self": 0.3604521099867952,
"children": {
"env_step": {
"total": 573.8075310730131,
"count": 22739,
"self": 406.51619994202497,
"children": {
"SubprocessEnvManager._take_step": {
"total": 166.94144458699986,
"count": 22739,
"self": 1.8074334590029366,
"children": {
"TorchPolicy.evaluate": {
"total": 165.13401112799693,
"count": 22739,
"self": 37.14995843699228,
"children": {
"TorchPolicy.sample_actions": {
"total": 127.98405269100465,
"count": 22739,
"self": 127.98405269100465
}
}
}
}
},
"workers": {
"total": 0.34988654398830477,
"count": 22739,
"self": 0.0,
"children": {
"worker_root": {
"total": 583.9534196789892,
"count": 22739,
"is_parallel": true,
"self": 299.143799367979,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00677219299996068,
"count": 1,
"is_parallel": true,
"self": 0.003577474999701735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003194718000258945,
"count": 10,
"is_parallel": true,
"self": 0.003194718000258945
}
}
},
"UnityEnvironment.step": {
"total": 0.044727267999974174,
"count": 1,
"is_parallel": true,
"self": 0.00048275300002842414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002798289999645931,
"count": 1,
"is_parallel": true,
"self": 0.0002798289999645931
},
"communicator.exchange": {
"total": 0.04218794899998102,
"count": 1,
"is_parallel": true,
"self": 0.04218794899998102
},
"steps_from_proto": {
"total": 0.0017767370000001392,
"count": 1,
"is_parallel": true,
"self": 0.00040706499976295163,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013696720002371876,
"count": 10,
"is_parallel": true,
"self": 0.0013696720002371876
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 284.80962031101024,
"count": 22738,
"is_parallel": true,
"self": 10.814832371008492,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.156108096000821,
"count": 22738,
"is_parallel": true,
"self": 6.156108096000821
},
"communicator.exchange": {
"total": 230.33834187398952,
"count": 22738,
"is_parallel": true,
"self": 230.33834187398952
},
"steps_from_proto": {
"total": 37.5003379700114,
"count": 22738,
"is_parallel": true,
"self": 8.21527906801441,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.28505890199699,
"count": 227380,
"is_parallel": true,
"self": 29.28505890199699
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.8863999861860066e-05,
"count": 1,
"self": 3.8863999861860066e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 570.2395306230342,
"count": 450788,
"is_parallel": true,
"self": 11.59562360102575,
"children": {
"process_trajectory": {
"total": 302.03710401900867,
"count": 450788,
"is_parallel": true,
"self": 301.2246548420087,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8124491769999622,
"count": 5,
"is_parallel": true,
"self": 0.8124491769999622
}
}
},
"_update_policy": {
"total": 256.60680300299975,
"count": 113,
"is_parallel": true,
"self": 52.9130335280048,
"children": {
"TorchPPOOptimizer.update": {
"total": 203.69376947499495,
"count": 11523,
"is_parallel": true,
"self": 203.69376947499495
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11326265499997135,
"count": 1,
"self": 0.0005757799999628332,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11268687500000851,
"count": 1,
"self": 0.11268687500000851
}
}
}
}
}
}
}