ppo-Huggy / run_logs /timers.json
Gare's picture
Huggy
4473b22 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4085965156555176,
"min": 1.4085965156555176,
"max": 1.4285900592803955,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69674.8203125,
"min": 69357.09375,
"max": 77549.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.10785824345146,
"min": 74.84242424242424,
"max": 416.375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49394.0,
"min": 48702.0,
"max": 50144.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999962.0,
"min": 49729.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999962.0,
"min": 49729.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.447897434234619,
"min": 0.01216465886682272,
"max": 2.50606632232666,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1591.13330078125,
"min": 1.447594404220581,
"max": 1606.1131591796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.834806089951442,
"min": 1.8255865795522177,
"max": 4.041643440400066,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2492.623958468437,
"min": 217.2448029667139,
"max": 2521.8356068730354,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.834806089951442,
"min": 1.8255865795522177,
"max": 4.041643440400066,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2492.623958468437,
"min": 217.2448029667139,
"max": 2521.8356068730354,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017042112088529394,
"min": 0.013248632837106318,
"max": 0.019359944884005623,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05112633626558818,
"min": 0.026497265674212636,
"max": 0.055714097898453475,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06314810543424554,
"min": 0.022569315197567146,
"max": 0.06314810543424554,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18944431630273662,
"min": 0.04513863039513429,
"max": 0.18944431630273662,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7684987438666716e-06,
"min": 3.7684987438666716e-06,
"max": 0.0002953467015510999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1305496231600015e-05,
"min": 1.1305496231600015e-05,
"max": 0.00084405856864715,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125613333333335,
"min": 0.10125613333333335,
"max": 0.19844889999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30376840000000005,
"min": 0.20766440000000003,
"max": 0.5813528500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.268105333333343e-05,
"min": 7.268105333333343e-05,
"max": 0.004922600109999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002180431600000003,
"min": 0.0002180431600000003,
"max": 0.014069507215000002,
"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": "1769760870",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769763378"
},
"total": 2508.1416846359994,
"count": 1,
"self": 0.4951339349991031,
"children": {
"run_training.setup": {
"total": 0.025023396000051434,
"count": 1,
"self": 0.025023396000051434
},
"TrainerController.start_learning": {
"total": 2507.621527305,
"count": 1,
"self": 4.103050737990998,
"children": {
"TrainerController._reset_env": {
"total": 3.317408591000003,
"count": 1,
"self": 3.317408591000003
},
"TrainerController.advance": {
"total": 2500.1076728960093,
"count": 232572,
"self": 4.338359281223802,
"children": {
"env_step": {
"total": 2050.468448024931,
"count": 232572,
"self": 1652.535161020989,
"children": {
"SubprocessEnvManager._take_step": {
"total": 395.2570214460575,
"count": 232572,
"self": 15.29241902127933,
"children": {
"TorchPolicy.evaluate": {
"total": 379.96460242477815,
"count": 222840,
"self": 379.96460242477815
}
}
},
"workers": {
"total": 2.6762655578845624,
"count": 232572,
"self": 0.0,
"children": {
"worker_root": {
"total": 2495.634711031913,
"count": 232572,
"is_parallel": true,
"self": 1156.565976870806,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008097730001281889,
"count": 1,
"is_parallel": true,
"self": 0.0002310060003765102,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005787669997516787,
"count": 2,
"is_parallel": true,
"self": 0.0005787669997516787
}
}
},
"UnityEnvironment.step": {
"total": 0.028995044000112102,
"count": 1,
"is_parallel": true,
"self": 0.00028709200023513404,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021110799980306183,
"count": 1,
"is_parallel": true,
"self": 0.00021110799980306183
},
"communicator.exchange": {
"total": 0.027722082999844133,
"count": 1,
"is_parallel": true,
"self": 0.027722082999844133
},
"steps_from_proto": {
"total": 0.0007747610002297733,
"count": 1,
"is_parallel": true,
"self": 0.00023236900051415432,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000542391999715619,
"count": 2,
"is_parallel": true,
"self": 0.000542391999715619
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1339.068734161107,
"count": 232571,
"is_parallel": true,
"self": 37.61564867003153,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.79575710598192,
"count": 232571,
"is_parallel": true,
"self": 82.79575710598192
},
"communicator.exchange": {
"total": 1129.9432814191123,
"count": 232571,
"is_parallel": true,
"self": 1129.9432814191123
},
"steps_from_proto": {
"total": 88.7140469659812,
"count": 232571,
"is_parallel": true,
"self": 31.671802408896838,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.04224455708436,
"count": 465142,
"is_parallel": true,
"self": 57.04224455708436
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 445.3008655898543,
"count": 232572,
"self": 5.941463611870404,
"children": {
"process_trajectory": {
"total": 151.65370036798322,
"count": 232572,
"self": 150.55518014698373,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0985202209994895,
"count": 10,
"self": 1.0985202209994895
}
}
},
"_update_policy": {
"total": 287.7057016100007,
"count": 97,
"self": 227.33206993298882,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.37363167701187,
"count": 2910,
"self": 60.37363167701187
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0320000001229346e-06,
"count": 1,
"self": 1.0320000001229346e-06
},
"TrainerController._save_models": {
"total": 0.09339404799993645,
"count": 1,
"self": 0.001312561000304413,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09208148699963203,
"count": 1,
"self": 0.09208148699963203
}
}
}
}
}
}
}