ppo-Huggy-v2 / run_logs /timers.json
astefani's picture
Huggy
85c25fb
raw
history blame contribute delete
No virus
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070463180541992,
"min": 1.4070463180541992,
"max": 1.4281694889068604,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70747.6953125,
"min": 68220.75,
"max": 76799.2734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 109.69315673289184,
"min": 82.87080536912751,
"max": 404.2258064516129,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49691.0,
"min": 48916.0,
"max": 50160.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999452.0,
"min": 49606.0,
"max": 1999452.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999452.0,
"min": 49606.0,
"max": 1999452.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3474740982055664,
"min": 0.21396513283252716,
"max": 2.4757511615753174,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1063.40576171875,
"min": 26.317710876464844,
"max": 1430.93994140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.545230078118263,
"min": 1.8419932506191052,
"max": 3.988353473590317,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1605.9892253875732,
"min": 226.56516982614994,
"max": 2287.9826765060425,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.545230078118263,
"min": 1.8419932506191052,
"max": 3.988353473590317,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1605.9892253875732,
"min": 226.56516982614994,
"max": 2287.9826765060425,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01659689858905848,
"min": 0.01403922280463045,
"max": 0.01923530843196204,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049790695767175444,
"min": 0.0280784456092609,
"max": 0.05484666920189435,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05028815157711506,
"min": 0.020169361773878333,
"max": 0.06170375417504046,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1508644547313452,
"min": 0.040338723547756666,
"max": 0.1851112625251214,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1816989394666622e-06,
"min": 3.1816989394666622e-06,
"max": 0.000295342126552625,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.545096818399986e-06,
"min": 9.545096818399986e-06,
"max": 0.0008442018185993998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10106053333333333,
"min": 0.10106053333333333,
"max": 0.19844737499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031816,
"min": 0.2072887,
"max": 0.5814005999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.292061333333327e-05,
"min": 6.292061333333327e-05,
"max": 0.0049225240124999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018876183999999983,
"min": 0.00018876183999999983,
"max": 0.014071889939999997,
"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": "1678980536",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy-v2 --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": "1678982924"
},
"total": 2388.7879949890003,
"count": 1,
"self": 0.3862264139997933,
"children": {
"run_training.setup": {
"total": 0.10323610900013591,
"count": 1,
"self": 0.10323610900013591
},
"TrainerController.start_learning": {
"total": 2388.2985324660003,
"count": 1,
"self": 4.285921167235756,
"children": {
"TrainerController._reset_env": {
"total": 6.265278402999684,
"count": 1,
"self": 6.265278402999684
},
"TrainerController.advance": {
"total": 2377.6300994357644,
"count": 232254,
"self": 4.68846332837893,
"children": {
"env_step": {
"total": 1862.5506103179769,
"count": 232254,
"self": 1564.8433548826524,
"children": {
"SubprocessEnvManager._take_step": {
"total": 294.86760350933037,
"count": 232254,
"self": 17.677927362123228,
"children": {
"TorchPolicy.evaluate": {
"total": 277.18967614720714,
"count": 223058,
"self": 277.18967614720714
}
}
},
"workers": {
"total": 2.839651925994076,
"count": 232254,
"self": 0.0,
"children": {
"worker_root": {
"total": 2380.065117427227,
"count": 232254,
"is_parallel": true,
"self": 1106.7022189663003,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009163340000668541,
"count": 1,
"is_parallel": true,
"self": 0.00035562100038077915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005607129996860749,
"count": 2,
"is_parallel": true,
"self": 0.0005607129996860749
}
}
},
"UnityEnvironment.step": {
"total": 0.06744166499993298,
"count": 1,
"is_parallel": true,
"self": 0.00027212799977860413,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022733600053470582,
"count": 1,
"is_parallel": true,
"self": 0.00022733600053470582
},
"communicator.exchange": {
"total": 0.06626707799932774,
"count": 1,
"is_parallel": true,
"self": 0.06626707799932774
},
"steps_from_proto": {
"total": 0.0006751230002919328,
"count": 1,
"is_parallel": true,
"self": 0.00020581900025717914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004693040000347537,
"count": 2,
"is_parallel": true,
"self": 0.0004693040000347537
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1273.3628984609268,
"count": 232253,
"is_parallel": true,
"self": 36.86776245988767,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.7775008849303,
"count": 232253,
"is_parallel": true,
"self": 79.7775008849303
},
"communicator.exchange": {
"total": 1066.8413599102332,
"count": 232253,
"is_parallel": true,
"self": 1066.8413599102332
},
"steps_from_proto": {
"total": 89.87627520587557,
"count": 232253,
"is_parallel": true,
"self": 35.94859156270195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.92768364317362,
"count": 464506,
"is_parallel": true,
"self": 53.92768364317362
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.39102578940856,
"count": 232254,
"self": 6.802563042406291,
"children": {
"process_trajectory": {
"total": 141.77668480200737,
"count": 232254,
"self": 140.35729588700724,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4193889150001269,
"count": 10,
"self": 1.4193889150001269
}
}
},
"_update_policy": {
"total": 361.8117779449949,
"count": 97,
"self": 304.3013372919859,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.51044065300903,
"count": 2910,
"self": 57.51044065300903
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0660005500540137e-06,
"count": 1,
"self": 1.0660005500540137e-06
},
"TrainerController._save_models": {
"total": 0.1172323939999842,
"count": 1,
"self": 0.0021261620004224824,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11510623199956171,
"count": 1,
"self": 0.11510623199956171
}
}
}
}
}
}
}