ppo-Huggy / run_logs /timers.json
kalbuld's picture
Huggy
d13813c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054877758026123,
"min": 1.4054877758026123,
"max": 1.4255917072296143,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70159.140625,
"min": 68204.0,
"max": 78561.71875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.15482695810564,
"min": 82.89597315436242,
"max": 421.4033613445378,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49495.0,
"min": 49166.0,
"max": 50147.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999906.0,
"min": 49945.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999906.0,
"min": 49945.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.45080304145813,
"min": 0.05784418061375618,
"max": 2.501224994659424,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1345.4908447265625,
"min": 6.825613498687744,
"max": 1438.445068359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7876419358783298,
"min": 1.914486601443614,
"max": 4.039342876742868,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2079.415422797203,
"min": 225.90941897034645,
"max": 2369.668391406536,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7876419358783298,
"min": 1.914486601443614,
"max": 4.039342876742868,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2079.415422797203,
"min": 225.90941897034645,
"max": 2369.668391406536,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015940068285757055,
"min": 0.013410922792293906,
"max": 0.02089342495613285,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04782020485727116,
"min": 0.026821845584587813,
"max": 0.054722267387357235,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05822208730710877,
"min": 0.020946524261186518,
"max": 0.06468864921480418,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1746662619213263,
"min": 0.041893048522373036,
"max": 0.1746662619213263,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.52249882586667e-06,
"min": 3.52249882586667e-06,
"max": 0.000295343026552325,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0567496477600011e-05,
"min": 1.0567496477600011e-05,
"max": 0.0008440986186337997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117413333333336,
"min": 0.10117413333333336,
"max": 0.19844767500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035224000000001,
"min": 0.20750829999999995,
"max": 0.5813661999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.858925333333339e-05,
"min": 6.858925333333339e-05,
"max": 0.0049225389825,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020576776000000017,
"min": 0.00020576776000000017,
"max": 0.014070173380000002,
"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": "1728314612",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728317030"
},
"total": 2418.19308953,
"count": 1,
"self": 0.6292053020006279,
"children": {
"run_training.setup": {
"total": 0.05320098599997891,
"count": 1,
"self": 0.05320098599997891
},
"TrainerController.start_learning": {
"total": 2417.5106832419997,
"count": 1,
"self": 4.2804481870671225,
"children": {
"TrainerController._reset_env": {
"total": 2.6185308760000225,
"count": 1,
"self": 2.6185308760000225
},
"TrainerController.advance": {
"total": 2410.4396001289324,
"count": 232342,
"self": 4.571531868934471,
"children": {
"env_step": {
"total": 1905.5214947860084,
"count": 232342,
"self": 1503.7036034808223,
"children": {
"SubprocessEnvManager._take_step": {
"total": 399.0760354390962,
"count": 232342,
"self": 15.516440486190447,
"children": {
"TorchPolicy.evaluate": {
"total": 383.55959495290574,
"count": 222932,
"self": 383.55959495290574
}
}
},
"workers": {
"total": 2.7418558660899635,
"count": 232342,
"self": 0.0,
"children": {
"worker_root": {
"total": 2410.0621520319114,
"count": 232342,
"is_parallel": true,
"self": 1192.4189572349362,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009095670000078826,
"count": 1,
"is_parallel": true,
"self": 0.00026826700002402504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006412999999838576,
"count": 2,
"is_parallel": true,
"self": 0.0006412999999838576
}
}
},
"UnityEnvironment.step": {
"total": 0.028024389000051997,
"count": 1,
"is_parallel": true,
"self": 0.0003955570001039632,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020244000000957385,
"count": 1,
"is_parallel": true,
"self": 0.00020244000000957385
},
"communicator.exchange": {
"total": 0.02674505599998156,
"count": 1,
"is_parallel": true,
"self": 0.02674505599998156
},
"steps_from_proto": {
"total": 0.0006813359999569002,
"count": 1,
"is_parallel": true,
"self": 0.00016560299991397187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005157330000429283,
"count": 2,
"is_parallel": true,
"self": 0.0005157330000429283
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1217.6431947969752,
"count": 232341,
"is_parallel": true,
"self": 37.22847068003762,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.6030958210498,
"count": 232341,
"is_parallel": true,
"self": 79.6030958210498
},
"communicator.exchange": {
"total": 1013.9033863499552,
"count": 232341,
"is_parallel": true,
"self": 1013.9033863499552
},
"steps_from_proto": {
"total": 86.90824194593267,
"count": 232341,
"is_parallel": true,
"self": 30.840496583804736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.06774536212794,
"count": 464682,
"is_parallel": true,
"self": 56.06774536212794
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 500.3465734739897,
"count": 232342,
"self": 6.4673733439690295,
"children": {
"process_trajectory": {
"total": 159.4778386720232,
"count": 232342,
"self": 158.1976188870231,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2802197850000994,
"count": 10,
"self": 1.2802197850000994
}
}
},
"_update_policy": {
"total": 334.40136145799744,
"count": 97,
"self": 268.1972417719954,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.20411968600206,
"count": 2910,
"self": 66.20411968600206
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4050001482246444e-06,
"count": 1,
"self": 1.4050001482246444e-06
},
"TrainerController._save_models": {
"total": 0.1721026449999954,
"count": 1,
"self": 0.0028786880002371618,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16922395699975823,
"count": 1,
"self": 0.16922395699975823
}
}
}
}
}
}
}