RomBor's picture
First Push
6888ef1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5681486129760742,
"min": 0.5042868852615356,
"max": 2.873913526535034,
"count": 200
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5862.1572265625,
"min": 4905.88720703125,
"max": 29494.974609375,
"count": 200
},
"SnowballTarget.Step.mean": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Step.sum": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.32640552520752,
"min": 0.21873608231544495,
"max": 14.532570838928223,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2936.9130859375,
"min": 42.43479919433594,
"max": 2964.64453125,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.066396962780809,
"min": 0.06031919120783534,
"max": 0.08020077417704491,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.33198481390404505,
"min": 0.24127676483134136,
"max": 0.40100387088522454,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1484619416442572,
"min": 0.10821494797482065,
"max": 0.26715927287644037,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.742309708221286,
"min": 0.4328597918992826,
"max": 1.3357963643822017,
"count": 200
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032997656000039e-07,
"min": 7.032997656000039e-07,
"max": 0.00029918820027059994,
"count": 200
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5164988280000196e-06,
"min": 3.5164988280000196e-06,
"max": 0.0014885160038279998,
"count": 200
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10023440000000002,
"min": 0.10023440000000002,
"max": 0.1997294,
"count": 200
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5011720000000001,
"min": 0.4029176,
"max": 0.996172,
"count": 200
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.1696560000000067e-05,
"min": 2.1696560000000067e-05,
"max": 0.004986497059999999,
"count": 200
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00010848280000000034,
"min": 0.00010848280000000034,
"max": 0.024808982800000004,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.2,
"min": 2.8863636363636362,
"max": 28.69090909090909,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1551.0,
"min": 127.0,
"max": 1578.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.2,
"min": 2.8863636363636362,
"max": 28.69090909090909,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1551.0,
"min": 127.0,
"max": 1578.0,
"count": 200
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1716258655",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716264994"
},
"total": 6338.507552372999,
"count": 1,
"self": 1.173160964998715,
"children": {
"run_training.setup": {
"total": 0.07310832899997877,
"count": 1,
"self": 0.07310832899997877
},
"TrainerController.start_learning": {
"total": 6337.261283079,
"count": 1,
"self": 8.518854030970942,
"children": {
"TrainerController._reset_env": {
"total": 3.912854601000163,
"count": 1,
"self": 3.912854601000163
},
"TrainerController.advance": {
"total": 6324.6905471930295,
"count": 181873,
"self": 4.432934625093367,
"children": {
"env_step": {
"total": 6320.257612567936,
"count": 181873,
"self": 4880.636477555219,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1434.6180167558953,
"count": 181873,
"self": 27.292887663914826,
"children": {
"TorchPolicy.evaluate": {
"total": 1407.3251290919804,
"count": 181873,
"self": 1407.3251290919804
}
}
},
"workers": {
"total": 5.003118256821381,
"count": 181873,
"self": 0.0,
"children": {
"worker_root": {
"total": 6316.631901943034,
"count": 181873,
"is_parallel": true,
"self": 2980.811726840072,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010583374999896478,
"count": 1,
"is_parallel": true,
"self": 0.004951687999891874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005631687000004604,
"count": 10,
"is_parallel": true,
"self": 0.005631687000004604
}
}
},
"UnityEnvironment.step": {
"total": 0.04740577799998391,
"count": 1,
"is_parallel": true,
"self": 0.0008714650000456459,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040437899997414206,
"count": 1,
"is_parallel": true,
"self": 0.00040437899997414206
},
"communicator.exchange": {
"total": 0.0437430829999812,
"count": 1,
"is_parallel": true,
"self": 0.0437430829999812
},
"steps_from_proto": {
"total": 0.0023868509999829257,
"count": 1,
"is_parallel": true,
"self": 0.00046004799992260814,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019268030000603176,
"count": 10,
"is_parallel": true,
"self": 0.0019268030000603176
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3335.820175102962,
"count": 181872,
"is_parallel": true,
"self": 157.71289303297817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.71062993895453,
"count": 181872,
"is_parallel": true,
"self": 80.71062993895453
},
"communicator.exchange": {
"total": 2636.3506341079956,
"count": 181872,
"is_parallel": true,
"self": 2636.3506341079956
},
"steps_from_proto": {
"total": 461.04601802303364,
"count": 181872,
"is_parallel": true,
"self": 91.75954009124825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 369.2864779317854,
"count": 1818720,
"is_parallel": true,
"self": 369.2864779317854
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0003868020003210404,
"count": 1,
"self": 0.0003868020003210404,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 6251.059646299031,
"count": 8266014,
"is_parallel": true,
"self": 188.00919848291232,
"children": {
"process_trajectory": {
"total": 3394.026778814128,
"count": 8266014,
"is_parallel": true,
"self": 3385.437743884131,
"children": {
"RLTrainer._checkpoint": {
"total": 8.58903492999707,
"count": 40,
"is_parallel": true,
"self": 8.58903492999707
}
}
},
"_update_policy": {
"total": 2669.0236690019897,
"count": 909,
"is_parallel": true,
"self": 688.7258904329826,
"children": {
"TorchPPOOptimizer.update": {
"total": 1980.297778569007,
"count": 46350,
"is_parallel": true,
"self": 1980.297778569007
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1386404519998905,
"count": 1,
"self": 0.0018547429999671294,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13678570899992337,
"count": 1,
"self": 0.13678570899992337
}
}
}
}
}
}
}