pratyushmathur's picture
First Push
a59345d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7764551639556885,
"min": 0.7764551639556885,
"max": 2.8215789794921875,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7379.4296875,
"min": 7379.4296875,
"max": 28802.677734375,
"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": 13.194686889648438,
"min": 0.3619472086429596,
"max": 13.30424690246582,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2572.9638671875,
"min": 70.21775817871094,
"max": 2718.6064453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06689714172624044,
"min": 0.06240587899593784,
"max": 0.07567467834508301,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26758856690496174,
"min": 0.26272620680581044,
"max": 0.3578114002576673,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1964388045610166,
"min": 0.13665707131126423,
"max": 0.32255339169619135,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7857552182440664,
"min": 0.5466282852450569,
"max": 1.3730334846996795,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0776097306000005e-05,
"min": 1.0776097306000005e-05,
"max": 0.000389176002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.310438922400002e-05,
"min": 4.310438922400002e-05,
"max": 0.0018468800382800002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10538800000000001,
"min": 0.10538800000000001,
"max": 0.29458799999999996,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.42155200000000004,
"min": 0.42155200000000004,
"max": 1.42344,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.5,
"min": 4.136363636363637,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 182.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 4.136363636363637,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 182.0,
"max": 1414.0,
"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": "1753776368",
"python_version": "3.10.12 (main, May 27 2025, 17:12:29) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1753776811"
},
"total": 442.48188822,
"count": 1,
"self": 0.3910318600001119,
"children": {
"run_training.setup": {
"total": 0.020489608999923803,
"count": 1,
"self": 0.020489608999923803
},
"TrainerController.start_learning": {
"total": 442.07036675099994,
"count": 1,
"self": 0.38254725999991024,
"children": {
"TrainerController._reset_env": {
"total": 3.400209030000042,
"count": 1,
"self": 3.400209030000042
},
"TrainerController.advance": {
"total": 438.1886983699999,
"count": 18192,
"self": 0.42217003598352676,
"children": {
"env_step": {
"total": 311.0451525930064,
"count": 18192,
"self": 237.1158317330037,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.68907299799639,
"count": 18192,
"self": 1.3595564429947444,
"children": {
"TorchPolicy.evaluate": {
"total": 72.32951655500165,
"count": 18192,
"self": 72.32951655500165
}
}
},
"workers": {
"total": 0.24024786200629933,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.47918774200366,
"count": 18192,
"is_parallel": true,
"self": 232.6072009550112,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005002043000104095,
"count": 1,
"is_parallel": true,
"self": 0.0034861120002460666,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015159309998580284,
"count": 10,
"is_parallel": true,
"self": 0.0015159309998580284
}
}
},
"UnityEnvironment.step": {
"total": 0.03681747499990706,
"count": 1,
"is_parallel": true,
"self": 0.0006111430000146356,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004399209999519371,
"count": 1,
"is_parallel": true,
"self": 0.0004399209999519371
},
"communicator.exchange": {
"total": 0.03378675099997963,
"count": 1,
"is_parallel": true,
"self": 0.03378675099997963
},
"steps_from_proto": {
"total": 0.001979659999960859,
"count": 1,
"is_parallel": true,
"self": 0.00039680999975644227,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015828500002044166,
"count": 10,
"is_parallel": true,
"self": 0.0015828500002044166
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.87198678699247,
"count": 18191,
"is_parallel": true,
"self": 10.101359918017124,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.531978344999061,
"count": 18191,
"is_parallel": true,
"self": 5.531978344999061
},
"communicator.exchange": {
"total": 159.16964222697698,
"count": 18191,
"is_parallel": true,
"self": 159.16964222697698
},
"steps_from_proto": {
"total": 33.069006296999305,
"count": 18191,
"is_parallel": true,
"self": 6.0909528279808,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.978053469018505,
"count": 181910,
"is_parallel": true,
"self": 26.978053469018505
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.72137574100998,
"count": 18192,
"self": 0.5125101829974028,
"children": {
"process_trajectory": {
"total": 28.388981965013045,
"count": 18192,
"self": 27.870468072012955,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5185138930000903,
"count": 4,
"self": 0.5185138930000903
}
}
},
"_update_policy": {
"total": 97.81988359299953,
"count": 90,
"self": 38.57562874200312,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.24425485099641,
"count": 4587,
"self": 59.24425485099641
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.490001957601635e-07,
"count": 1,
"self": 9.490001957601635e-07
},
"TrainerController._save_models": {
"total": 0.09891114199990625,
"count": 1,
"self": 0.0011096179998730804,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09780152400003317,
"count": 1,
"self": 0.09780152400003317
}
}
}
}
}
}
}