PaulTbbr's picture
First Push
d0e9e23 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7855961322784424,
"min": 0.7522308826446533,
"max": 2.854323387145996,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8079.85595703125,
"min": 6968.009765625,
"max": 29582.890625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.80102825164795,
"min": 0.5273751616477966,
"max": 13.889245986938477,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1393.90380859375,
"min": 51.155391693115234,
"max": 1420.9559326171875,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.90566037735849,
"min": 4.590909090909091,
"max": 27.528301886792452,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1426.0,
"min": 202.0,
"max": 1500.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.90566037735849,
"min": 4.590909090909091,
"max": 27.528301886792452,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1426.0,
"min": 202.0,
"max": 1500.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0706031675779206,
"min": 0.05844538613846274,
"max": 0.07847299272418204,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.35301583788960295,
"min": 0.23378154455385097,
"max": 0.3923649636209102,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.162031541121941,
"min": 0.15905845062989815,
"max": 0.30567985458993446,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8101577056097049,
"min": 0.640297165980526,
"max": 1.4484163169182982,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.000099000000003e-06,
"min": 3.000099000000003e-06,
"max": 0.0002967000011,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5000495000000015e-05,
"min": 1.5000495000000015e-05,
"max": 0.0014538000154,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101,
"min": 0.101,
"max": 0.19890000000000002,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.505,
"min": 0.41192000000000006,
"max": 0.9846000000000001,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 5.9900000000000047e-05,
"min": 5.9900000000000047e-05,
"max": 0.00494511,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00029950000000000023,
"min": 0.00029950000000000023,
"max": 0.024231540000000003,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1711910969",
"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=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711912238"
},
"total": 1269.331869646,
"count": 1,
"self": 0.49331525700017664,
"children": {
"run_training.setup": {
"total": 0.09995147799997994,
"count": 1,
"self": 0.09995147799997994
},
"TrainerController.start_learning": {
"total": 1268.7386029109998,
"count": 1,
"self": 1.7896298090290657,
"children": {
"TrainerController._reset_env": {
"total": 3.61966818399992,
"count": 1,
"self": 3.61966818399992
},
"TrainerController.advance": {
"total": 1263.136199706971,
"count": 45549,
"self": 0.8693825129778361,
"children": {
"env_step": {
"total": 1262.2668171939931,
"count": 45549,
"self": 799.4751858580075,
"children": {
"SubprocessEnvManager._take_step": {
"total": 461.89165997797954,
"count": 45549,
"self": 4.434828821973724,
"children": {
"TorchPolicy.evaluate": {
"total": 457.4568311560058,
"count": 45549,
"self": 457.4568311560058
}
}
},
"workers": {
"total": 0.8999713580060416,
"count": 45549,
"self": 0.0,
"children": {
"worker_root": {
"total": 1264.7884437870268,
"count": 45549,
"is_parallel": true,
"self": 604.0081909900478,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010980506999999307,
"count": 1,
"is_parallel": true,
"self": 0.0052514710001787535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005729035999820553,
"count": 10,
"is_parallel": true,
"self": 0.005729035999820553
}
}
},
"UnityEnvironment.step": {
"total": 0.09189107100007732,
"count": 1,
"is_parallel": true,
"self": 0.0009545119999074814,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046635200010314293,
"count": 1,
"is_parallel": true,
"self": 0.00046635200010314293
},
"communicator.exchange": {
"total": 0.08753799900000558,
"count": 1,
"is_parallel": true,
"self": 0.08753799900000558
},
"steps_from_proto": {
"total": 0.0029322080000611095,
"count": 1,
"is_parallel": true,
"self": 0.0006010200000901023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023311879999710072,
"count": 10,
"is_parallel": true,
"self": 0.0023311879999710072
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 660.7802527969791,
"count": 45548,
"is_parallel": true,
"self": 30.463776162985255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 15.391914735984756,
"count": 45548,
"is_parallel": true,
"self": 15.391914735984756
},
"communicator.exchange": {
"total": 519.2573805429879,
"count": 45548,
"is_parallel": true,
"self": 519.2573805429879
},
"steps_from_proto": {
"total": 95.66718135502117,
"count": 45548,
"is_parallel": true,
"self": 18.42261674109875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.24456461392242,
"count": 455480,
"is_parallel": true,
"self": 77.24456461392242
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000772503999996843,
"count": 1,
"self": 0.000772503999996843,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1250.7491818339215,
"count": 1519387,
"is_parallel": true,
"self": 33.53253266208617,
"children": {
"process_trajectory": {
"total": 561.6681466898335,
"count": 1519387,
"is_parallel": true,
"self": 558.4414686368334,
"children": {
"RLTrainer._checkpoint": {
"total": 3.2266780530001142,
"count": 10,
"is_parallel": true,
"self": 3.2266780530001142
}
}
},
"_update_policy": {
"total": 655.5485024820019,
"count": 227,
"is_parallel": true,
"self": 156.73636252800816,
"children": {
"TorchPPOOptimizer.update": {
"total": 498.8121399539938,
"count": 11577,
"is_parallel": true,
"self": 498.8121399539938
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1923327069998777,
"count": 1,
"self": 0.0032472439997945912,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1890854630000831,
"count": 1,
"self": 0.1890854630000831
}
}
}
}
}
}
}