bguisard's picture
First model
37788ed
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9351761341094971,
"min": 0.9351761341094971,
"max": 2.8761091232299805,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8929.0615234375,
"min": 8929.0615234375,
"max": 29454.234375,
"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": 12.991866111755371,
"min": 0.4339427351951599,
"max": 12.991866111755371,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2533.413818359375,
"min": 84.18489074707031,
"max": 2649.99755859375,
"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": 0.06996762349459174,
"min": 0.062253894912325504,
"max": 0.07554114506787943,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27987049397836694,
"min": 0.26649081306737465,
"max": 0.3590413846297238,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23840472058338277,
"min": 0.13805749961494596,
"max": 0.2908519657657427,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9536188823335311,
"min": 0.5522299984597838,
"max": 1.3426582693469291,
"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": 24.90909090909091,
"min": 3.8863636363636362,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1096.0,
"min": 171.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.90909090909091,
"min": 3.8863636363636362,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1096.0,
"min": 171.0,
"max": 1415.0,
"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": "1674243759",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1674244236"
},
"total": 476.87088358699987,
"count": 1,
"self": 0.33175021099975766,
"children": {
"run_training.setup": {
"total": 0.15171330700002272,
"count": 1,
"self": 0.15171330700002272
},
"TrainerController.start_learning": {
"total": 476.3874200690001,
"count": 1,
"self": 0.5596182250061474,
"children": {
"TrainerController._reset_env": {
"total": 8.655667658000084,
"count": 1,
"self": 8.655667658000084
},
"TrainerController.advance": {
"total": 467.0252252499936,
"count": 18201,
"self": 0.3051258419873193,
"children": {
"env_step": {
"total": 466.72009940800626,
"count": 18201,
"self": 303.91503107099277,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.5162773420135,
"count": 18201,
"self": 1.5661875760131352,
"children": {
"TorchPolicy.evaluate": {
"total": 160.95008976600036,
"count": 18201,
"self": 31.47707073100935,
"children": {
"TorchPolicy.sample_actions": {
"total": 129.473019034991,
"count": 18201,
"self": 129.473019034991
}
}
}
}
},
"workers": {
"total": 0.2887909949999994,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 475.43685502698634,
"count": 18201,
"is_parallel": true,
"self": 256.25014168897155,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00734320399999433,
"count": 1,
"is_parallel": true,
"self": 0.004151933999878565,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0031912700001157646,
"count": 10,
"is_parallel": true,
"self": 0.0031912700001157646
}
}
},
"UnityEnvironment.step": {
"total": 0.04210940100006155,
"count": 1,
"is_parallel": true,
"self": 0.0005447810000305253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039062799999101117,
"count": 1,
"is_parallel": true,
"self": 0.00039062799999101117
},
"communicator.exchange": {
"total": 0.03882099500003733,
"count": 1,
"is_parallel": true,
"self": 0.03882099500003733
},
"steps_from_proto": {
"total": 0.002352997000002688,
"count": 1,
"is_parallel": true,
"self": 0.00061762899997575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017353680000269378,
"count": 10,
"is_parallel": true,
"self": 0.0017353680000269378
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.18671333801478,
"count": 18200,
"is_parallel": true,
"self": 9.003744643036953,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.664052298991919,
"count": 18200,
"is_parallel": true,
"self": 5.664052298991919
},
"communicator.exchange": {
"total": 169.48860552798976,
"count": 18200,
"is_parallel": true,
"self": 169.48860552798976
},
"steps_from_proto": {
"total": 35.03031086799615,
"count": 18200,
"is_parallel": true,
"self": 7.91414155900668,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.11616930898947,
"count": 182000,
"is_parallel": true,
"self": 27.11616930898947
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.0193000131694134e-05,
"count": 1,
"self": 4.0193000131694134e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 463.8555488829884,
"count": 391010,
"is_parallel": true,
"self": 9.194281316834235,
"children": {
"process_trajectory": {
"total": 251.50632690715554,
"count": 391010,
"is_parallel": true,
"self": 250.5990527911555,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9072741160000533,
"count": 4,
"is_parallel": true,
"self": 0.9072741160000533
}
}
},
"_update_policy": {
"total": 203.1549406589986,
"count": 90,
"is_parallel": true,
"self": 49.20205442100462,
"children": {
"TorchPPOOptimizer.update": {
"total": 153.952886237994,
"count": 4587,
"is_parallel": true,
"self": 153.952886237994
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14686874300014097,
"count": 1,
"self": 0.0008789579999302077,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14598978500021076,
"count": 1,
"self": 0.14598978500021076
}
}
}
}
}
}
}