mbarekat's picture
First Push
c96437f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.049878716468811,
"min": 1.0482120513916016,
"max": 2.862600326538086,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10047.33984375,
"min": 10047.33984375,
"max": 29410.35546875,
"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": 12.071637153625488,
"min": 0.38976263999938965,
"max": 12.071637153625488,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2353.96923828125,
"min": 75.61395263671875,
"max": 2439.806396484375,
"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": 0.07413542882753901,
"min": 0.060556277080596535,
"max": 0.07446596080576544,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29654171531015605,
"min": 0.24222510832238614,
"max": 0.3719778950366091,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19038572169694246,
"min": 0.13250083493881437,
"max": 0.2814251230481793,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7615428867877698,
"min": 0.5300033397552575,
"max": 1.3155855199541238,
"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": 24.09090909090909,
"min": 3.5454545454545454,
"max": 24.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1060.0,
"min": 156.0,
"max": 1302.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.09090909090909,
"min": 3.5454545454545454,
"max": 24.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1060.0,
"min": 156.0,
"max": 1302.0,
"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": "1694842377",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1694842885"
},
"total": 508.636189455,
"count": 1,
"self": 0.7861356260001457,
"children": {
"run_training.setup": {
"total": 0.041113265999911164,
"count": 1,
"self": 0.041113265999911164
},
"TrainerController.start_learning": {
"total": 507.80894056299996,
"count": 1,
"self": 0.6435070370039284,
"children": {
"TrainerController._reset_env": {
"total": 4.177756941000098,
"count": 1,
"self": 4.177756941000098
},
"TrainerController.advance": {
"total": 502.732759560996,
"count": 18211,
"self": 0.30495263999557665,
"children": {
"env_step": {
"total": 502.4278069210004,
"count": 18211,
"self": 367.2656028280155,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.84640909299003,
"count": 18211,
"self": 1.8930453419948208,
"children": {
"TorchPolicy.evaluate": {
"total": 132.9533637509952,
"count": 18211,
"self": 132.9533637509952
}
}
},
"workers": {
"total": 0.31579499999486416,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 506.0025202550006,
"count": 18211,
"is_parallel": true,
"self": 236.45678734100136,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00582883499998843,
"count": 1,
"is_parallel": true,
"self": 0.004225010000141083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016038249998473475,
"count": 10,
"is_parallel": true,
"self": 0.0016038249998473475
}
}
},
"UnityEnvironment.step": {
"total": 0.07188457699999162,
"count": 1,
"is_parallel": true,
"self": 0.0007756080000262955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004316839999773947,
"count": 1,
"is_parallel": true,
"self": 0.0004316839999773947
},
"communicator.exchange": {
"total": 0.0653879249999818,
"count": 1,
"is_parallel": true,
"self": 0.0653879249999818
},
"steps_from_proto": {
"total": 0.005289360000006127,
"count": 1,
"is_parallel": true,
"self": 0.0005574870000373267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0047318729999688,
"count": 10,
"is_parallel": true,
"self": 0.0047318729999688
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 269.54573291399925,
"count": 18210,
"is_parallel": true,
"self": 11.205810744006385,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.880706485998644,
"count": 18210,
"is_parallel": true,
"self": 5.880706485998644
},
"communicator.exchange": {
"total": 212.6743784729896,
"count": 18210,
"is_parallel": true,
"self": 212.6743784729896
},
"steps_from_proto": {
"total": 39.78483721100463,
"count": 18210,
"is_parallel": true,
"self": 7.457102655004178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.32773455600045,
"count": 182100,
"is_parallel": true,
"self": 32.32773455600045
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001600539999344619,
"count": 1,
"self": 0.0001600539999344619,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 498.74085907399046,
"count": 466806,
"is_parallel": true,
"self": 10.904793673956078,
"children": {
"process_trajectory": {
"total": 275.98718094403444,
"count": 466806,
"is_parallel": true,
"self": 273.8039750100346,
"children": {
"RLTrainer._checkpoint": {
"total": 2.1832059339998295,
"count": 4,
"is_parallel": true,
"self": 2.1832059339998295
}
}
},
"_update_policy": {
"total": 211.84888445599995,
"count": 90,
"is_parallel": true,
"self": 81.6974675440008,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.15141691199915,
"count": 4584,
"is_parallel": true,
"self": 130.15141691199915
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.25475697000001674,
"count": 1,
"self": 0.0012874060000740428,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2534695639999427,
"count": 1,
"self": 0.2534695639999427
}
}
}
}
}
}
}