ppo-Huggy / run_logs /timers.json
Sugutt's picture
Huggy
d1af937 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4071863889694214,
"min": 1.4071801900863647,
"max": 1.4253178834915161,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70501.4453125,
"min": 69460.328125,
"max": 76356.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.4718196457327,
"min": 75.0920245398773,
"max": 396.3015873015873,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49352.0,
"min": 48894.0,
"max": 50136.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49759.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49759.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.489297389984131,
"min": 0.1189584955573082,
"max": 2.489297389984131,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1545.8536376953125,
"min": 14.86981201171875,
"max": 1605.3887939453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.931366024673849,
"min": 1.736218064546585,
"max": 4.000371502910013,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2441.37830132246,
"min": 217.02725806832314,
"max": 2559.6349596381187,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.931366024673849,
"min": 1.736218064546585,
"max": 4.000371502910013,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2441.37830132246,
"min": 217.02725806832314,
"max": 2559.6349596381187,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016611387902190067,
"min": 0.012010451939083093,
"max": 0.021371334358506525,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049834163706570206,
"min": 0.024020903878166185,
"max": 0.05593755644125242,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05612707936929332,
"min": 0.022019186057150364,
"max": 0.05923628248274326,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16838123810787997,
"min": 0.04403837211430073,
"max": 0.17132182382047179,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.836348721250008e-06,
"min": 3.836348721250008e-06,
"max": 0.0002953656015448,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1509046163750022e-05,
"min": 1.1509046163750022e-05,
"max": 0.00084436696854435,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127875000000001,
"min": 0.10127875000000001,
"max": 0.19845519999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30383625000000003,
"min": 0.20770265,
"max": 0.5814556500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.380962500000013e-05,
"min": 7.380962500000013e-05,
"max": 0.00492291448,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002214288750000004,
"min": 0.0002214288750000004,
"max": 0.014074636934999999,
"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": "1741249144",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741251526"
},
"total": 2382.2778859269997,
"count": 1,
"self": 0.44064972799969837,
"children": {
"run_training.setup": {
"total": 0.023000263000085397,
"count": 1,
"self": 0.023000263000085397
},
"TrainerController.start_learning": {
"total": 2381.814235936,
"count": 1,
"self": 4.132621481030583,
"children": {
"TrainerController._reset_env": {
"total": 3.24702894699999,
"count": 1,
"self": 3.24702894699999
},
"TrainerController.advance": {
"total": 2374.3201226309684,
"count": 232835,
"self": 4.060550411983968,
"children": {
"env_step": {
"total": 1880.8136594109842,
"count": 232835,
"self": 1475.62575101198,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.67239296300204,
"count": 232835,
"self": 15.347363713838831,
"children": {
"TorchPolicy.evaluate": {
"total": 387.3250292491632,
"count": 222904,
"self": 387.3250292491632
}
}
},
"workers": {
"total": 2.5155154360022607,
"count": 232835,
"self": 0.0,
"children": {
"worker_root": {
"total": 2374.902388074102,
"count": 232835,
"is_parallel": true,
"self": 1170.31180160924,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011483030000363215,
"count": 1,
"is_parallel": true,
"self": 0.0002450179999868851,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009032850000494363,
"count": 2,
"is_parallel": true,
"self": 0.0009032850000494363
}
}
},
"UnityEnvironment.step": {
"total": 0.03106847000003654,
"count": 1,
"is_parallel": true,
"self": 0.00030524399994646956,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018103900015375984,
"count": 1,
"is_parallel": true,
"self": 0.00018103900015375984
},
"communicator.exchange": {
"total": 0.029867546999867045,
"count": 1,
"is_parallel": true,
"self": 0.029867546999867045
},
"steps_from_proto": {
"total": 0.0007146400000692665,
"count": 1,
"is_parallel": true,
"self": 0.00018699500014918158,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000527644999920085,
"count": 2,
"is_parallel": true,
"self": 0.000527644999920085
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1204.5905864648619,
"count": 232834,
"is_parallel": true,
"self": 36.01612001291414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.72157412911861,
"count": 232834,
"is_parallel": true,
"self": 77.72157412911861
},
"communicator.exchange": {
"total": 1006.3988707861031,
"count": 232834,
"is_parallel": true,
"self": 1006.3988707861031
},
"steps_from_proto": {
"total": 84.45402153672603,
"count": 232834,
"is_parallel": true,
"self": 29.401227752734258,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.052793783991774,
"count": 465668,
"is_parallel": true,
"self": 55.052793783991774
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 489.44591280800023,
"count": 232835,
"self": 6.113807823115167,
"children": {
"process_trajectory": {
"total": 161.2289642888852,
"count": 232835,
"self": 159.8844582068848,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3445060820004073,
"count": 10,
"self": 1.3445060820004073
}
}
},
"_update_policy": {
"total": 322.10314069599985,
"count": 97,
"self": 256.9363108449852,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.16682985101465,
"count": 2910,
"self": 65.16682985101465
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.330005923402496e-07,
"count": 1,
"self": 9.330005923402496e-07
},
"TrainerController._save_models": {
"total": 0.11446194400014065,
"count": 1,
"self": 0.0017882149995784857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11267372900056216,
"count": 1,
"self": 0.11267372900056216
}
}
}
}
}
}
}