ppo-Huggy / run_logs /timers.json
npit's picture
Huggy
5c7180e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4041849374771118,
"min": 1.4041849374771118,
"max": 1.4253774881362915,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69024.1171875,
"min": 69024.1171875,
"max": 76092.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.09724473257698,
"min": 74.88449848024317,
"max": 410.60655737704917,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49420.0,
"min": 49009.0,
"max": 50094.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49949.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49949.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4408175945281982,
"min": 0.07665093243122101,
"max": 2.5061984062194824,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1505.9844970703125,
"min": 9.274763107299805,
"max": 1616.2791748046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.747248575308721,
"min": 1.7314564775336871,
"max": 3.9922670578335318,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2312.052370965481,
"min": 209.50623378157616,
"max": 2511.1938584446907,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.747248575308721,
"min": 1.7314564775336871,
"max": 3.9922670578335318,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2312.052370965481,
"min": 209.50623378157616,
"max": 2511.1938584446907,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016059604889273438,
"min": 0.014211142396986058,
"max": 0.020920813580839116,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04817881466782031,
"min": 0.028422284793972116,
"max": 0.05720935976472295,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05692796106967662,
"min": 0.022360502555966378,
"max": 0.08906648711611827,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17078388320902985,
"min": 0.04597752708941698,
"max": 0.18898299013574918,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.696648767816665e-06,
"min": 3.696648767816665e-06,
"max": 0.00029532945155684995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1089946303449995e-05,
"min": 1.1089946303449995e-05,
"max": 0.0008439534186821998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123218333333335,
"min": 0.10123218333333335,
"max": 0.19844315,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30369655000000007,
"min": 0.20760984999999998,
"max": 0.5813178,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.148594833333331e-05,
"min": 7.148594833333331e-05,
"max": 0.004922313184999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021445784499999994,
"min": 0.00021445784499999994,
"max": 0.014067758219999997,
"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": "1671992701",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1671995022"
},
"total": 2320.3273503769997,
"count": 1,
"self": 0.3924930649995986,
"children": {
"run_training.setup": {
"total": 0.23052727599997525,
"count": 1,
"self": 0.23052727599997525
},
"TrainerController.start_learning": {
"total": 2319.704330036,
"count": 1,
"self": 4.086645014047008,
"children": {
"TrainerController._reset_env": {
"total": 8.146367597999983,
"count": 1,
"self": 8.146367597999983
},
"TrainerController.advance": {
"total": 2307.353015805953,
"count": 233234,
"self": 4.269470660009574,
"children": {
"env_step": {
"total": 1829.7510231969889,
"count": 233234,
"self": 1538.335181741975,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.6545789470421,
"count": 233234,
"self": 14.782444778033266,
"children": {
"TorchPolicy.evaluate": {
"total": 273.87213416900886,
"count": 222944,
"self": 67.51633008501813,
"children": {
"TorchPolicy.sample_actions": {
"total": 206.35580408399073,
"count": 222944,
"self": 206.35580408399073
}
}
}
}
},
"workers": {
"total": 2.7612625079717645,
"count": 233234,
"self": 0.0,
"children": {
"worker_root": {
"total": 2311.558540549032,
"count": 233234,
"is_parallel": true,
"self": 1047.649785257087,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020557920000214835,
"count": 1,
"is_parallel": true,
"self": 0.0003397880000193254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017160040000021581,
"count": 2,
"is_parallel": true,
"self": 0.0017160040000021581
}
}
},
"UnityEnvironment.step": {
"total": 0.028311191000000235,
"count": 1,
"is_parallel": true,
"self": 0.0002945230000364063,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021440599999777987,
"count": 1,
"is_parallel": true,
"self": 0.00021440599999777987
},
"communicator.exchange": {
"total": 0.026989068999967003,
"count": 1,
"is_parallel": true,
"self": 0.026989068999967003
},
"steps_from_proto": {
"total": 0.0008131929999990462,
"count": 1,
"is_parallel": true,
"self": 0.0002726100000245424,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005405829999745038,
"count": 2,
"is_parallel": true,
"self": 0.0005405829999745038
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.908755291945,
"count": 233233,
"is_parallel": true,
"self": 35.202363660980154,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.18116392001758,
"count": 233233,
"is_parallel": true,
"self": 82.18116392001758
},
"communicator.exchange": {
"total": 1048.5365636469596,
"count": 233233,
"is_parallel": true,
"self": 1048.5365636469596
},
"steps_from_proto": {
"total": 97.98866406398776,
"count": 233233,
"is_parallel": true,
"self": 42.80973958589908,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.178924478088675,
"count": 466466,
"is_parallel": true,
"self": 55.178924478088675
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 473.3325219489544,
"count": 233234,
"self": 5.974419390001742,
"children": {
"process_trajectory": {
"total": 158.27252922295304,
"count": 233234,
"self": 157.02441611695292,
"children": {
"RLTrainer._checkpoint": {
"total": 1.248113106000119,
"count": 10,
"self": 1.248113106000119
}
}
},
"_update_policy": {
"total": 309.08557333599964,
"count": 97,
"self": 256.3719935989948,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.71357973700486,
"count": 2910,
"self": 52.71357973700486
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.630002750782296e-07,
"count": 1,
"self": 9.630002750782296e-07
},
"TrainerController._save_models": {
"total": 0.11830065499998454,
"count": 1,
"self": 0.0022106149999672198,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11609004000001732,
"count": 1,
"self": 0.11609004000001732
}
}
}
}
}
}
}