ppo-Huggy / run_logs /timers.json
gsn-codes's picture
Huggy
262c23f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.40621817111969,
"min": 1.40621817111969,
"max": 1.4264734983444214,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72105.2421875,
"min": 68580.5546875,
"max": 75567.1953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 110.9205298013245,
"min": 87.1443661971831,
"max": 390.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50247.0,
"min": 49143.0,
"max": 50247.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999995.0,
"min": 49946.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999995.0,
"min": 49946.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.270604372024536,
"min": 0.0857229009270668,
"max": 2.4386355876922607,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1028.583740234375,
"min": 10.886808395385742,
"max": 1375.3905029296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4641822201526717,
"min": 1.9536505188998274,
"max": 3.8516161675360188,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1569.2745457291603,
"min": 248.1136159002781,
"max": 2172.3115184903145,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4641822201526717,
"min": 1.9536505188998274,
"max": 3.8516161675360188,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1569.2745457291603,
"min": 248.1136159002781,
"max": 2172.3115184903145,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01826868385625049,
"min": 0.014002609980533029,
"max": 0.019701116834767163,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05480605156875148,
"min": 0.028006083807364725,
"max": 0.05910335050430149,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04238712878690826,
"min": 0.022329472471028566,
"max": 0.05751849133521318,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12716138636072477,
"min": 0.04465894494205713,
"max": 0.1700255701939265,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.388798870433334e-06,
"min": 3.388798870433334e-06,
"max": 0.00029527822657392504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0166396611300002e-05,
"min": 1.0166396611300002e-05,
"max": 0.0008438562187146,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112956666666666,
"min": 0.10112956666666666,
"max": 0.198426075,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30338869999999996,
"min": 0.20742055000000004,
"max": 0.5812854000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.636537666666668e-05,
"min": 6.636537666666668e-05,
"max": 0.0049214611425,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019909613000000006,
"min": 0.00019909613000000006,
"max": 0.014066141459999997,
"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": "1685652478",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 --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": "1685655006"
},
"total": 2527.9440928970002,
"count": 1,
"self": 0.4492060800002946,
"children": {
"run_training.setup": {
"total": 0.04366444499999034,
"count": 1,
"self": 0.04366444499999034
},
"TrainerController.start_learning": {
"total": 2527.451222372,
"count": 1,
"self": 4.515141458010476,
"children": {
"TrainerController._reset_env": {
"total": 3.7423442900000055,
"count": 1,
"self": 3.7423442900000055
},
"TrainerController.advance": {
"total": 2519.0801022899896,
"count": 232279,
"self": 4.810675594807435,
"children": {
"env_step": {
"total": 1980.9436347540773,
"count": 232279,
"self": 1677.9697630312203,
"children": {
"SubprocessEnvManager._take_step": {
"total": 299.9778801029104,
"count": 232279,
"self": 17.71254898886542,
"children": {
"TorchPolicy.evaluate": {
"total": 282.26533111404495,
"count": 223102,
"self": 282.26533111404495
}
}
},
"workers": {
"total": 2.995991619946608,
"count": 232279,
"self": 0.0,
"children": {
"worker_root": {
"total": 2519.2428495190893,
"count": 232279,
"is_parallel": true,
"self": 1148.89292087614,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00101068200001464,
"count": 1,
"is_parallel": true,
"self": 0.0002943169999980455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007163650000165944,
"count": 2,
"is_parallel": true,
"self": 0.0007163650000165944
}
}
},
"UnityEnvironment.step": {
"total": 0.028675736999957735,
"count": 1,
"is_parallel": true,
"self": 0.0003400429999942389,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002505639999981213,
"count": 1,
"is_parallel": true,
"self": 0.0002505639999981213
},
"communicator.exchange": {
"total": 0.02734424299995908,
"count": 1,
"is_parallel": true,
"self": 0.02734424299995908
},
"steps_from_proto": {
"total": 0.0007408870000062961,
"count": 1,
"is_parallel": true,
"self": 0.0002423089999865624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004985780000197337,
"count": 2,
"is_parallel": true,
"self": 0.0004985780000197337
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1370.3499286429494,
"count": 232278,
"is_parallel": true,
"self": 40.09136726402835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.14169322597479,
"count": 232278,
"is_parallel": true,
"self": 85.14169322597479
},
"communicator.exchange": {
"total": 1146.1216844019984,
"count": 232278,
"is_parallel": true,
"self": 1146.1216844019984
},
"steps_from_proto": {
"total": 98.99518375094789,
"count": 232278,
"is_parallel": true,
"self": 39.06324780886507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.931935942082816,
"count": 464556,
"is_parallel": true,
"self": 59.931935942082816
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.3257919411051,
"count": 232279,
"self": 6.744125196137247,
"children": {
"process_trajectory": {
"total": 142.74587844696833,
"count": 232279,
"self": 141.36642973696888,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3794487099994512,
"count": 10,
"self": 1.3794487099994512
}
}
},
"_update_policy": {
"total": 383.83578829799944,
"count": 97,
"self": 323.7445680539894,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.09122024401006,
"count": 2910,
"self": 60.09122024401006
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.22000253922306e-07,
"count": 1,
"self": 9.22000253922306e-07
},
"TrainerController._save_models": {
"total": 0.11363341199967181,
"count": 1,
"self": 0.001993495999613515,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11163991600005829,
"count": 1,
"self": 0.11163991600005829
}
}
}
}
}
}
}