wooihen's picture
Third training of SnowballTarget
413ec7d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7358174324035645,
"min": 0.7325859665870667,
"max": 0.9828445911407471,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7559.7880859375,
"min": 7328.9951171875,
"max": 10054.5,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 299944.0,
"min": 209936.0,
"max": 299944.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 299944.0,
"min": 209936.0,
"max": 299944.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.153875350952148,
"min": 12.569143295288086,
"max": 13.153875350952148,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2683.390625,
"min": 2425.9951171875,
"max": 2683.390625,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06698446306257334,
"min": 0.06698446306257334,
"max": 0.07733593310546769,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3349223153128667,
"min": 0.2747376191352184,
"max": 0.38667966552733846,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18880830830803105,
"min": 0.17042047125013435,
"max": 0.20299850503603617,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9440415415401553,
"min": 0.6816818850005374,
"max": 1.0149925251801808,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.3760982079999995e-06,
"min": 5.3760982079999995e-06,
"max": 9.4476068508e-05,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.688049104e-05,
"min": 2.688049104e-05,
"max": 0.0004228803590399999,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10179200000000002,
"min": 0.10179200000000002,
"max": 0.131492,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5089600000000001,
"min": 0.420368,
"max": 0.64096,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.942080000000004e-05,
"min": 9.942080000000004e-05,
"max": 0.0015814508000000001,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004971040000000002,
"min": 0.0004971040000000002,
"max": 0.007083904000000002,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.545454545454547,
"min": 24.472727272727273,
"max": 26.15909090909091,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1405.0,
"min": 1099.0,
"max": 1414.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 24.472727272727273,
"max": 26.15909090909091,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1405.0,
"min": 1099.0,
"max": 1414.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674566751",
"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 --resume",
"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": "1674566965"
},
"total": 213.47065103399996,
"count": 1,
"self": 0.38094927400015877,
"children": {
"run_training.setup": {
"total": 0.09994892499980779,
"count": 1,
"self": 0.09994892499980779
},
"TrainerController.start_learning": {
"total": 212.989752835,
"count": 1,
"self": 0.30431898299707427,
"children": {
"TrainerController._reset_env": {
"total": 5.767107357999976,
"count": 1,
"self": 5.767107357999976
},
"TrainerController.advance": {
"total": 206.798572978003,
"count": 9137,
"self": 0.12693639499661913,
"children": {
"env_step": {
"total": 206.67163658300638,
"count": 9137,
"self": 133.55333972800372,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.99586036600022,
"count": 9137,
"self": 0.679882864995534,
"children": {
"TorchPolicy.evaluate": {
"total": 72.31597750100468,
"count": 9137,
"self": 16.044926747004183,
"children": {
"TorchPolicy.sample_actions": {
"total": 56.2710507540005,
"count": 9137,
"self": 56.2710507540005
}
}
}
}
},
"workers": {
"total": 0.12243648900243898,
"count": 9137,
"self": 0.0,
"children": {
"worker_root": {
"total": 212.35592430900647,
"count": 9137,
"is_parallel": true,
"self": 105.31660526099995,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017697550001685158,
"count": 1,
"is_parallel": true,
"self": 0.0006437490001189872,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011260060000495287,
"count": 10,
"is_parallel": true,
"self": 0.0011260060000495287
}
}
},
"UnityEnvironment.step": {
"total": 0.03381327900001452,
"count": 1,
"is_parallel": true,
"self": 0.0003282200002558966,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002813270000388002,
"count": 1,
"is_parallel": true,
"self": 0.0002813270000388002
},
"communicator.exchange": {
"total": 0.03163155799984452,
"count": 1,
"is_parallel": true,
"self": 0.03163155799984452
},
"steps_from_proto": {
"total": 0.0015721739998753037,
"count": 1,
"is_parallel": true,
"self": 0.00042703099984464643,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011451430000306573,
"count": 10,
"is_parallel": true,
"self": 0.0011451430000306573
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 107.03931904800652,
"count": 9136,
"is_parallel": true,
"self": 4.015640574009467,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.632346284995947,
"count": 9136,
"is_parallel": true,
"self": 2.632346284995947
},
"communicator.exchange": {
"total": 85.71767279699907,
"count": 9136,
"is_parallel": true,
"self": 85.71767279699907
},
"steps_from_proto": {
"total": 14.673659392002037,
"count": 9136,
"is_parallel": true,
"self": 3.17473373702569,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.498925654976347,
"count": 91360,
"is_parallel": true,
"self": 11.498925654976347
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.110199999260658e-05,
"count": 1,
"self": 7.110199999260658e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 205.3860190179962,
"count": 170915,
"is_parallel": true,
"self": 4.482775567014869,
"children": {
"process_trajectory": {
"total": 118.99587218098122,
"count": 170915,
"is_parallel": true,
"self": 118.5729203249814,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4229518559998269,
"count": 2,
"is_parallel": true,
"self": 0.4229518559998269
}
}
},
"_update_policy": {
"total": 81.90737127000011,
"count": 45,
"is_parallel": true,
"self": 19.832407818994625,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.07496345100549,
"count": 2292,
"is_parallel": true,
"self": 62.07496345100549
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1196824139999535,
"count": 1,
"self": 0.0010140509998564085,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11866836300009709,
"count": 1,
"self": 0.11866836300009709
}
}
}
}
}
}
}