ppo-Huggy / run_logs /timers.json
pratyushmathur's picture
Huggy
136f6b3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4036879539489746,
"min": 1.4036879539489746,
"max": 1.428206443786621,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70110.0,
"min": 68225.078125,
"max": 75704.8671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.74762808349146,
"min": 86.48877374784111,
"max": 400.48,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49405.0,
"min": 48758.0,
"max": 50186.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49847.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49847.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3545432090759277,
"min": -0.0008715159492567182,
"max": 2.431621789932251,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1240.84423828125,
"min": -0.10806797444820404,
"max": 1376.927490234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6808360177154107,
"min": 1.8382009145232938,
"max": 3.9039989499681034,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1939.8005813360214,
"min": 227.93691340088844,
"max": 2215.538180708885,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6808360177154107,
"min": 1.8382009145232938,
"max": 3.9039989499681034,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1939.8005813360214,
"min": 227.93691340088844,
"max": 2215.538180708885,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01910013950061208,
"min": 0.01349096323150055,
"max": 0.019644679087731574,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03820027900122416,
"min": 0.0269819264630011,
"max": 0.05893403726319472,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05283757454405229,
"min": 0.02294538337737322,
"max": 0.06645067563901344,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10567514908810458,
"min": 0.04589076675474644,
"max": 0.19882824768622714,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.5792984736e-06,
"min": 4.5792984736e-06,
"max": 0.00029531167656277497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.1585969472e-06,
"min": 9.1585969472e-06,
"max": 0.0008441280186239999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10152640000000002,
"min": 0.10152640000000002,
"max": 0.19843722500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20305280000000003,
"min": 0.20305280000000003,
"max": 0.5813759999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.616736000000002e-05,
"min": 8.616736000000002e-05,
"max": 0.004922017527500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017233472000000003,
"min": 0.00017233472000000003,
"max": 0.014070662400000003,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1748585572",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748588031"
},
"total": 2459.539967082,
"count": 1,
"self": 0.6451689740001711,
"children": {
"run_training.setup": {
"total": 0.030019675999938045,
"count": 1,
"self": 0.030019675999938045
},
"TrainerController.start_learning": {
"total": 2458.864778432,
"count": 1,
"self": 4.300898245920507,
"children": {
"TrainerController._reset_env": {
"total": 3.842678363999994,
"count": 1,
"self": 3.842678363999994
},
"TrainerController.advance": {
"total": 2450.57594880908,
"count": 231412,
"self": 4.670615765039656,
"children": {
"env_step": {
"total": 1943.871596236979,
"count": 231412,
"self": 1529.5768859088862,
"children": {
"SubprocessEnvManager._take_step": {
"total": 411.6479603980413,
"count": 231412,
"self": 15.778249815014306,
"children": {
"TorchPolicy.evaluate": {
"total": 395.869710583027,
"count": 222946,
"self": 395.869710583027
}
}
},
"workers": {
"total": 2.6467499300515556,
"count": 231412,
"self": 0.0,
"children": {
"worker_root": {
"total": 2451.3300496389907,
"count": 231412,
"is_parallel": true,
"self": 1204.4165071609948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008840699999836943,
"count": 1,
"is_parallel": true,
"self": 0.00024818900010359357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006358809998801007,
"count": 2,
"is_parallel": true,
"self": 0.0006358809998801007
}
}
},
"UnityEnvironment.step": {
"total": 0.031043675000091753,
"count": 1,
"is_parallel": true,
"self": 0.0003256420000070648,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018861000012293516,
"count": 1,
"is_parallel": true,
"self": 0.00018861000012293516
},
"communicator.exchange": {
"total": 0.02982509100002062,
"count": 1,
"is_parallel": true,
"self": 0.02982509100002062
},
"steps_from_proto": {
"total": 0.0007043319999411324,
"count": 1,
"is_parallel": true,
"self": 0.00019996899982288596,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005043630001182464,
"count": 2,
"is_parallel": true,
"self": 0.0005043630001182464
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1246.9135424779959,
"count": 231411,
"is_parallel": true,
"self": 37.1430526889269,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.54872693214747,
"count": 231411,
"is_parallel": true,
"self": 83.54872693214747
},
"communicator.exchange": {
"total": 1038.0820254560417,
"count": 231411,
"is_parallel": true,
"self": 1038.0820254560417
},
"steps_from_proto": {
"total": 88.13973740087977,
"count": 231411,
"is_parallel": true,
"self": 33.03552797908765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.10420942179212,
"count": 462822,
"is_parallel": true,
"self": 55.10420942179212
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 502.0337368070609,
"count": 231412,
"self": 6.372588789100519,
"children": {
"process_trajectory": {
"total": 156.74430421596162,
"count": 231412,
"self": 155.3841751419618,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3601290739998149,
"count": 10,
"self": 1.3601290739998149
}
}
},
"_update_policy": {
"total": 338.91684380199877,
"count": 96,
"self": 273.86645891098897,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.0503848910098,
"count": 2880,
"self": 65.0503848910098
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2240002433827613e-06,
"count": 1,
"self": 1.2240002433827613e-06
},
"TrainerController._save_models": {
"total": 0.145251788999758,
"count": 1,
"self": 0.0032230319998234336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14202875699993456,
"count": 1,
"self": 0.14202875699993456
}
}
}
}
}
}
}