thuyentruong's picture
First Push
9e0de69
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": -3.576278402306343e-07,
"min": -3.576278402306343e-07,
"max": 0.7023292183876038,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": -0.0036860702093690634,
"min": -0.0036860702093690634,
"max": 7192.55322265625,
"count": 2
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.1046575978398323,
"min": -0.15264254808425903,
"max": -0.1046575978398323,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": -21.45480728149414,
"min": -29.612655639648438,
"max": -21.45480728149414,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0676529473247915,
"min": 0.0676529473247915,
"max": 0.17359924140071278,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3382647366239575,
"min": 0.3382647366239575,
"max": 0.6943969656028511,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.0008314786798020541,
"min": 0.0008314786798020541,
"max": 3.240200660954168,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.004157393399010271,
"min": 0.004157393399010271,
"max": 12.960802643816672,
"count": 2
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.00703200007656,
"min": 0.00703200007656,
"max": 0.02188200002706,
"count": 2
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0351600003828,
"min": 0.0351600003828,
"max": 0.08752800010824,
"count": 2
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.12344000000000002,
"min": 0.12344000000000002,
"max": 0.17294,
"count": 2
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.6172000000000001,
"min": 0.6172000000000001,
"max": 0.69176,
"count": 2
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0011796560000000003,
"min": 0.0011796560000000003,
"max": 0.003649706,
"count": 2
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.005898280000000001,
"min": 0.005898280000000001,
"max": 0.014598824,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 44.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 44.0,
"count": 2
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683597647",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683597698"
},
"total": 51.258182063999925,
"count": 1,
"self": 0.5474232689998644,
"children": {
"run_training.setup": {
"total": 0.04845362399998976,
"count": 1,
"self": 0.04845362399998976
},
"TrainerController.start_learning": {
"total": 50.66230517100007,
"count": 1,
"self": 0.08969771600015974,
"children": {
"TrainerController._reset_env": {
"total": 4.061605265000026,
"count": 1,
"self": 4.061605265000026
},
"TrainerController.advance": {
"total": 46.34825296199995,
"count": 1869,
"self": 0.029370799998446273,
"children": {
"env_step": {
"total": 46.3188821620015,
"count": 1869,
"self": 32.828526125996405,
"children": {
"SubprocessEnvManager._take_step": {
"total": 13.463007039006243,
"count": 1869,
"self": 0.17441184000642806,
"children": {
"TorchPolicy.evaluate": {
"total": 13.288595198999815,
"count": 1869,
"self": 13.288595198999815
}
}
},
"workers": {
"total": 0.02734899699885318,
"count": 1869,
"self": 0.0,
"children": {
"worker_root": {
"total": 50.334363330997576,
"count": 1869,
"is_parallel": true,
"self": 25.951789083995322,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0048623270000689445,
"count": 1,
"is_parallel": true,
"self": 0.003614632000335405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012476949997335396,
"count": 10,
"is_parallel": true,
"self": 0.0012476949997335396
}
}
},
"UnityEnvironment.step": {
"total": 0.0405810099999826,
"count": 1,
"is_parallel": true,
"self": 0.0005217939999511145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032942500001809094,
"count": 1,
"is_parallel": true,
"self": 0.00032942500001809094
},
"communicator.exchange": {
"total": 0.038125662999959786,
"count": 1,
"is_parallel": true,
"self": 0.038125662999959786
},
"steps_from_proto": {
"total": 0.0016041280000536062,
"count": 1,
"is_parallel": true,
"self": 0.00029592899988983845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013081990001637678,
"count": 10,
"is_parallel": true,
"self": 0.0013081990001637678
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 24.382574247002253,
"count": 1868,
"is_parallel": true,
"self": 1.0605107400104998,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.5648367209961407,
"count": 1868,
"is_parallel": true,
"self": 0.5648367209961407
},
"communicator.exchange": {
"total": 19.172753690995364,
"count": 1868,
"is_parallel": true,
"self": 19.172753690995364
},
"steps_from_proto": {
"total": 3.5844730950002486,
"count": 1868,
"is_parallel": true,
"self": 0.6909337430050755,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.893539351995173,
"count": 18680,
"is_parallel": true,
"self": 2.893539351995173
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002663249999841355,
"count": 1,
"self": 0.0002663249999841355,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 46.01376450299961,
"count": 46632,
"is_parallel": true,
"self": 1.009007445997554,
"children": {
"process_trajectory": {
"total": 26.335937168002147,
"count": 46632,
"is_parallel": true,
"self": 26.335937168002147
},
"_update_policy": {
"total": 18.668819888999906,
"count": 9,
"is_parallel": true,
"self": 6.679155762000619,
"children": {
"TorchPPOOptimizer.update": {
"total": 11.989664126999287,
"count": 456,
"is_parallel": true,
"self": 11.989664126999287
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1624829029999546,
"count": 1,
"self": 0.0008457950000320125,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1616371079999226,
"count": 1,
"self": 0.1616371079999226
}
}
}
}
}
}
}