ppo-Huggy / run_logs /timers.json
Nack34's picture
Huggy
1c176be verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054747819900513,
"min": 1.4054747819900513,
"max": 1.4262068271636963,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69263.203125,
"min": 68427.5859375,
"max": 79341.7578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.71688741721854,
"min": 74.81942336874052,
"max": 432.6068376068376,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49357.0,
"min": 49259.0,
"max": 50615.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999953.0,
"min": 49983.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999953.0,
"min": 49983.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4312920570373535,
"min": 0.08935761451721191,
"max": 2.514042615890503,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1468.5003662109375,
"min": 10.365483283996582,
"max": 1592.99169921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7406633417337933,
"min": 1.765925168605714,
"max": 4.081118230693108,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2259.3606584072113,
"min": 204.84731955826283,
"max": 2506.7949714660645,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7406633417337933,
"min": 1.765925168605714,
"max": 4.081118230693108,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2259.3606584072113,
"min": 204.84731955826283,
"max": 2506.7949714660645,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019559516199579876,
"min": 0.013819052333342874,
"max": 0.02011355248808589,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.058678548598739624,
"min": 0.030249709156729903,
"max": 0.05952740756280643,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05732537118924989,
"min": 0.020552566771705943,
"max": 0.05842858888208866,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17197611356774967,
"min": 0.04110513354341189,
"max": 0.172850576415658,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6652487782833293e-06,
"min": 3.6652487782833293e-06,
"max": 0.00029537520154159993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0995746334849988e-05,
"min": 1.0995746334849988e-05,
"max": 0.0008442369185877,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012217166666667,
"min": 0.1012217166666667,
"max": 0.19845839999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036651500000001,
"min": 0.2075902,
"max": 0.5814123000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.096366166666657e-05,
"min": 7.096366166666657e-05,
"max": 0.00492307416,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021289098499999973,
"min": 0.00021289098499999973,
"max": 0.014072473769999996,
"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": "1742653874",
"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": "1742656292"
},
"total": 2418.0545589149997,
"count": 1,
"self": 0.4942188319996603,
"children": {
"run_training.setup": {
"total": 0.022618996999995034,
"count": 1,
"self": 0.022618996999995034
},
"TrainerController.start_learning": {
"total": 2417.537721086,
"count": 1,
"self": 4.379310824965614,
"children": {
"TrainerController._reset_env": {
"total": 3.500614599999949,
"count": 1,
"self": 3.500614599999949
},
"TrainerController.advance": {
"total": 2409.5461799700342,
"count": 233151,
"self": 4.616245241032175,
"children": {
"env_step": {
"total": 1908.859584464001,
"count": 233151,
"self": 1492.2710671480131,
"children": {
"SubprocessEnvManager._take_step": {
"total": 413.89871464595024,
"count": 233151,
"self": 15.352327939983752,
"children": {
"TorchPolicy.evaluate": {
"total": 398.5463867059665,
"count": 222928,
"self": 398.5463867059665
}
}
},
"workers": {
"total": 2.6898026700375794,
"count": 233151,
"self": 0.0,
"children": {
"worker_root": {
"total": 2409.993871072032,
"count": 233151,
"is_parallel": true,
"self": 1193.5917172650989,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010738869999613598,
"count": 1,
"is_parallel": true,
"self": 0.00035257100000762875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007213159999537311,
"count": 2,
"is_parallel": true,
"self": 0.0007213159999537311
}
}
},
"UnityEnvironment.step": {
"total": 0.029097997000008036,
"count": 1,
"is_parallel": true,
"self": 0.0003102829999761525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017767100007404224,
"count": 1,
"is_parallel": true,
"self": 0.00017767100007404224
},
"communicator.exchange": {
"total": 0.02791468700002042,
"count": 1,
"is_parallel": true,
"self": 0.02791468700002042
},
"steps_from_proto": {
"total": 0.0006953559999374193,
"count": 1,
"is_parallel": true,
"self": 0.0001790799999525916,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005162759999848276,
"count": 2,
"is_parallel": true,
"self": 0.0005162759999848276
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1216.4021538069333,
"count": 233150,
"is_parallel": true,
"self": 37.179320066949,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.95027358697553,
"count": 233150,
"is_parallel": true,
"self": 78.95027358697553
},
"communicator.exchange": {
"total": 1014.5180252890293,
"count": 233150,
"is_parallel": true,
"self": 1014.5180252890293
},
"steps_from_proto": {
"total": 85.75453486397942,
"count": 233150,
"is_parallel": true,
"self": 30.0213081799252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.733226684054216,
"count": 466300,
"is_parallel": true,
"self": 55.733226684054216
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 496.07035026500114,
"count": 233151,
"self": 6.672580493034047,
"children": {
"process_trajectory": {
"total": 166.01945894396965,
"count": 233151,
"self": 164.74814353297018,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2713154109994775,
"count": 10,
"self": 1.2713154109994775
}
}
},
"_update_policy": {
"total": 323.37831082799744,
"count": 97,
"self": 256.81959552500246,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.55871530299498,
"count": 2910,
"self": 66.55871530299498
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.950000847107731e-07,
"count": 1,
"self": 8.950000847107731e-07
},
"TrainerController._save_models": {
"total": 0.1116147960001399,
"count": 1,
"self": 0.0018277069998475781,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10978708900029233,
"count": 1,
"self": 0.10978708900029233
}
}
}
}
}
}
}