jimjiang203's picture
First model push
6b3f30b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": -3.576278402306343e-07,
"min": -3.576278402306343e-07,
"max": 0.6270020604133606,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": -0.0034185645636171103,
"min": -0.0036860702093690634,
"max": 6428.02490234375,
"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": 0.0031717538367956877,
"min": -0.03686489909887314,
"max": 0.0049997917376458645,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.6184920072555542,
"min": -7.151790618896484,
"max": 1.0199575424194336,
"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": 0.0653819996400225,
"min": 0.06419295240178982,
"max": 0.14083556993379415,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26152799856009,
"min": 0.2567718096071593,
"max": 0.5633422797351766,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 1.4869749532845518e-05,
"min": 1.3001024359148097e-05,
"max": 322.4647458659975,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 5.947899813138207e-05,
"min": 5.745186459138245e-05,
"max": 1289.85898346399,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.001347000097306001,
"min": 0.001347000097306001,
"max": 0.04864700000270601,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.005388000389224004,
"min": 0.005388000389224004,
"max": 0.23086000003828003,
"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": 0.0,
"min": 0.0,
"max": 0.8181818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 36.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.8181818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 36.0,
"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": "1719579617",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719580047"
},
"total": 429.6964784659999,
"count": 1,
"self": 0.4249309470001208,
"children": {
"run_training.setup": {
"total": 0.07610302499961108,
"count": 1,
"self": 0.07610302499961108
},
"TrainerController.start_learning": {
"total": 429.1954444940002,
"count": 1,
"self": 0.5483462620036335,
"children": {
"TrainerController._reset_env": {
"total": 2.92004316800012,
"count": 1,
"self": 2.92004316800012
},
"TrainerController.advance": {
"total": 425.63874754399603,
"count": 18202,
"self": 0.2667180619937426,
"children": {
"env_step": {
"total": 425.3720294820023,
"count": 18202,
"self": 270.04188939302503,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.0543094580171,
"count": 18202,
"self": 1.4406679380090281,
"children": {
"TorchPolicy.evaluate": {
"total": 153.61364152000806,
"count": 18202,
"self": 153.61364152000806
}
}
},
"workers": {
"total": 0.27583063096017213,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.9282036689665,
"count": 18202,
"is_parallel": true,
"self": 227.30470915795604,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002898317000017414,
"count": 1,
"is_parallel": true,
"self": 0.0007315580010072154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021667589990101987,
"count": 10,
"is_parallel": true,
"self": 0.0021667589990101987
}
}
},
"UnityEnvironment.step": {
"total": 0.041576238999823545,
"count": 1,
"is_parallel": true,
"self": 0.0006295649995990971,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003987660002167104,
"count": 1,
"is_parallel": true,
"self": 0.0003987660002167104
},
"communicator.exchange": {
"total": 0.038644737000140594,
"count": 1,
"is_parallel": true,
"self": 0.038644737000140594
},
"steps_from_proto": {
"total": 0.0019031709998671431,
"count": 1,
"is_parallel": true,
"self": 0.000372070000594249,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015311009992728941,
"count": 10,
"is_parallel": true,
"self": 0.0015311009992728941
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.62349451101045,
"count": 18201,
"is_parallel": true,
"self": 10.094619112072905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.343198521982686,
"count": 18201,
"is_parallel": true,
"self": 5.343198521982686
},
"communicator.exchange": {
"total": 151.213497765998,
"count": 18201,
"is_parallel": true,
"self": 151.213497765998
},
"steps_from_proto": {
"total": 33.97217911095686,
"count": 18201,
"is_parallel": true,
"self": 6.504058340904976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.468120770051883,
"count": 182010,
"is_parallel": true,
"self": 27.468120770051883
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011823400018329266,
"count": 1,
"self": 0.00011823400018329266,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 420.43164133383425,
"count": 628604,
"is_parallel": true,
"self": 13.144507115160195,
"children": {
"process_trajectory": {
"total": 232.33192482367394,
"count": 628604,
"is_parallel": true,
"self": 231.5352226676746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7967021559993555,
"count": 4,
"is_parallel": true,
"self": 0.7967021559993555
}
}
},
"_update_policy": {
"total": 174.9552093950001,
"count": 90,
"is_parallel": true,
"self": 53.98603316800927,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.96917622699084,
"count": 4587,
"is_parallel": true,
"self": 120.96917622699084
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08818928600021536,
"count": 1,
"self": 0.0009118399998442328,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08727744600037113,
"count": 1,
"self": 0.08727744600037113
}
}
}
}
}
}
}