rgny's picture
First Push
8419054
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9308348894119263,
"min": 0.9308348894119263,
"max": 2.8640482425689697,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8887.611328125,
"min": 8887.611328125,
"max": 29425.23046875,
"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": 12.78643798828125,
"min": 0.2769193649291992,
"max": 12.78643798828125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.35546875,
"min": 53.72235870361328,
"max": 2605.5244140625,
"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": 0.07422264724708856,
"min": 0.06073397230576637,
"max": 0.07916683065830547,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29689058898835424,
"min": 0.24293588922306547,
"max": 0.3958341532915274,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1940697597376272,
"min": 0.11587665226611801,
"max": 0.2695283415855146,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7762790389505088,
"min": 0.46350660906447205,
"max": 1.3476417079275729,
"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": 24.84090909090909,
"min": 3.1818181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 140.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.1818181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 140.0,
"max": 1400.0,
"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": "1703666095",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703666525"
},
"total": 429.37563309000006,
"count": 1,
"self": 0.43474382200020045,
"children": {
"run_training.setup": {
"total": 0.0803378299999622,
"count": 1,
"self": 0.0803378299999622
},
"TrainerController.start_learning": {
"total": 428.8605514379999,
"count": 1,
"self": 0.548798614017187,
"children": {
"TrainerController._reset_env": {
"total": 3.3235489280000365,
"count": 1,
"self": 3.3235489280000365
},
"TrainerController.advance": {
"total": 424.8954685679828,
"count": 18199,
"self": 0.25487684899530905,
"children": {
"env_step": {
"total": 424.6405917189875,
"count": 18199,
"self": 276.2200575799677,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.15232705699282,
"count": 18199,
"self": 1.3945937500100172,
"children": {
"TorchPolicy.evaluate": {
"total": 146.7577333069828,
"count": 18199,
"self": 146.7577333069828
}
}
},
"workers": {
"total": 0.2682070820269473,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.68439679697735,
"count": 18199,
"is_parallel": true,
"self": 211.71860457798698,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005308741000135342,
"count": 1,
"is_parallel": true,
"self": 0.004014316000848339,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012944249992870027,
"count": 10,
"is_parallel": true,
"self": 0.0012944249992870027
}
}
},
"UnityEnvironment.step": {
"total": 0.040248392999956195,
"count": 1,
"is_parallel": true,
"self": 0.0006078810001781676,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042872199992416427,
"count": 1,
"is_parallel": true,
"self": 0.00042872199992416427
},
"communicator.exchange": {
"total": 0.03733411700000033,
"count": 1,
"is_parallel": true,
"self": 0.03733411700000033
},
"steps_from_proto": {
"total": 0.0018776729998535302,
"count": 1,
"is_parallel": true,
"self": 0.00037098099983268185,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015066920000208484,
"count": 10,
"is_parallel": true,
"self": 0.0015066920000208484
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.96579221899037,
"count": 18198,
"is_parallel": true,
"self": 10.363420566999139,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.1384072570001535,
"count": 18198,
"is_parallel": true,
"self": 5.1384072570001535
},
"communicator.exchange": {
"total": 168.03863552099824,
"count": 18198,
"is_parallel": true,
"self": 168.03863552099824
},
"steps_from_proto": {
"total": 32.42532887399284,
"count": 18198,
"is_parallel": true,
"self": 5.878671638021842,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.546657235970997,
"count": 181980,
"is_parallel": true,
"self": 26.546657235970997
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012432699986675289,
"count": 1,
"self": 0.00012432699986675289,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 419.4551695728776,
"count": 666929,
"is_parallel": true,
"self": 13.89631130585235,
"children": {
"process_trajectory": {
"total": 232.65010848102565,
"count": 666929,
"is_parallel": true,
"self": 232.17872820702564,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4713802740000119,
"count": 4,
"is_parallel": true,
"self": 0.4713802740000119
}
}
},
"_update_policy": {
"total": 172.9087497859996,
"count": 90,
"is_parallel": true,
"self": 53.134476058010705,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.77427372798888,
"count": 4587,
"is_parallel": true,
"self": 119.77427372798888
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09261100100002295,
"count": 1,
"self": 0.0009243649999461923,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09168663600007676,
"count": 1,
"self": 0.09168663600007676
}
}
}
}
}
}
}