ppo-Huggy / run_logs /timers.json
qJakc's picture
Huggy
c4700e5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4064644575119019,
"min": 1.4064644575119019,
"max": 1.4266034364700317,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71977.2265625,
"min": 69109.1484375,
"max": 77725.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.17272727272727,
"min": 83.7,
"max": 377.593984962406,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49045.0,
"min": 48899.0,
"max": 50220.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49685.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49685.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4011688232421875,
"min": 0.15352563560009003,
"max": 2.461583137512207,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1320.642822265625,
"min": 20.265384674072266,
"max": 1420.6025390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.661528430743651,
"min": 1.7354740536574162,
"max": 3.9206743527758294,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2013.840636909008,
"min": 229.08257508277893,
"max": 2172.539131999016,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.661528430743651,
"min": 1.7354740536574162,
"max": 3.9206743527758294,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2013.840636909008,
"min": 229.08257508277893,
"max": 2172.539131999016,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015421409482951278,
"min": 0.014097106305416673,
"max": 0.01974251455394551,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046264228448853834,
"min": 0.028194212610833345,
"max": 0.055869698857228894,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048080741200182166,
"min": 0.02159140376995007,
"max": 0.05902157177527746,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1442422236005465,
"min": 0.04318280753990014,
"max": 0.16662531433006128,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.299298900266668e-06,
"min": 3.299298900266668e-06,
"max": 0.000295353226548925,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.897896700800005e-06,
"min": 9.897896700800005e-06,
"max": 0.0008439951186682997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109973333333334,
"min": 0.10109973333333334,
"max": 0.19845107499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30329920000000005,
"min": 0.2073408,
"max": 0.5813317,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.487669333333338e-05,
"min": 6.487669333333338e-05,
"max": 0.0049227086425,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019463008000000014,
"min": 0.00019463008000000014,
"max": 0.014068451829999998,
"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": "1700074316",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700076950"
},
"total": 2633.794950949,
"count": 1,
"self": 0.4885839879998457,
"children": {
"run_training.setup": {
"total": 0.05500020499994207,
"count": 1,
"self": 0.05500020499994207
},
"TrainerController.start_learning": {
"total": 2633.251366756,
"count": 1,
"self": 5.041766029984501,
"children": {
"TrainerController._reset_env": {
"total": 8.659649749000096,
"count": 1,
"self": 8.659649749000096
},
"TrainerController.advance": {
"total": 2619.442109106016,
"count": 232281,
"self": 5.154101255892783,
"children": {
"env_step": {
"total": 2080.217586438144,
"count": 232281,
"self": 1711.9913740730647,
"children": {
"SubprocessEnvManager._take_step": {
"total": 364.90425538005024,
"count": 232281,
"self": 18.678769719041497,
"children": {
"TorchPolicy.evaluate": {
"total": 346.22548566100875,
"count": 223076,
"self": 346.22548566100875
}
}
},
"workers": {
"total": 3.321956985028919,
"count": 232281,
"self": 0.0,
"children": {
"worker_root": {
"total": 2625.291982766902,
"count": 232281,
"is_parallel": true,
"self": 1240.131301745917,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008332289999088971,
"count": 1,
"is_parallel": true,
"self": 0.00023821899992526596,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005950099999836311,
"count": 2,
"is_parallel": true,
"self": 0.0005950099999836311
}
}
},
"UnityEnvironment.step": {
"total": 0.051859471999932794,
"count": 1,
"is_parallel": true,
"self": 0.00035687899980985094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018387500006156188,
"count": 1,
"is_parallel": true,
"self": 0.00018387500006156188
},
"communicator.exchange": {
"total": 0.05055435600002056,
"count": 1,
"is_parallel": true,
"self": 0.05055435600002056
},
"steps_from_proto": {
"total": 0.0007643620000408191,
"count": 1,
"is_parallel": true,
"self": 0.00020799200001420104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005563700000266181,
"count": 2,
"is_parallel": true,
"self": 0.0005563700000266181
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1385.160681020985,
"count": 232280,
"is_parallel": true,
"self": 42.62411689005762,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.41052596500379,
"count": 232280,
"is_parallel": true,
"self": 87.41052596500379
},
"communicator.exchange": {
"total": 1158.6244790399421,
"count": 232280,
"is_parallel": true,
"self": 1158.6244790399421
},
"steps_from_proto": {
"total": 96.50155912598143,
"count": 232280,
"is_parallel": true,
"self": 33.317981619780426,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.183577506201004,
"count": 464560,
"is_parallel": true,
"self": 63.183577506201004
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 534.0704214119794,
"count": 232281,
"self": 7.701957093996043,
"children": {
"process_trajectory": {
"total": 162.90485023298447,
"count": 232281,
"self": 161.74372700398487,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1611232289995996,
"count": 10,
"self": 1.1611232289995996
}
}
},
"_update_policy": {
"total": 363.4636140849989,
"count": 97,
"self": 298.299707206004,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.16390687899491,
"count": 2910,
"self": 65.16390687899491
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0619996828609146e-06,
"count": 1,
"self": 1.0619996828609146e-06
},
"TrainerController._save_models": {
"total": 0.10784080900020854,
"count": 1,
"self": 0.0019679470005939947,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10587286199961454,
"count": 1,
"self": 0.10587286199961454
}
}
}
}
}
}
}