trsdimi's picture
First version
b87da5b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0079865455627441,
"min": 1.0079865455627441,
"max": 2.8399341106414795,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 50327.7578125,
"min": 50327.7578125,
"max": 143731.90625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 49952.0,
"max": 999952.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 49952.0,
"max": 999952.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.430911660194397,
"min": 0.14780384302139282,
"max": 1.4342303276062012,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 714.02490234375,
"min": 73.45851135253906,
"max": 715.680908203125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 48158.0,
"min": 48158.0,
"max": 50347.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.193548387096776,
"min": 4.60655737704918,
"max": 28.193548387096776,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 6992.0,
"min": 1124.0,
"max": 7086.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.193548387096776,
"min": 4.60655737704918,
"max": 28.193548387096776,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 6992.0,
"min": 1124.0,
"max": 7086.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.049235143672128626,
"min": 0.047167973132828986,
"max": 0.05223672624725817,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24617571836064311,
"min": 0.18867189253131594,
"max": 0.26118363123629085,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.06920753929196369,
"min": 0.05212089103225264,
"max": 0.10589725350340207,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.34603769645981847,
"min": 0.20848356412901056,
"max": 0.5294862675170103,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.274497575200001e-06,
"min": 7.274497575200001e-06,
"max": 0.00029197140267620003,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.6372487876000006e-05,
"min": 3.6372487876000006e-05,
"max": 0.001385688038104,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10242480000000001,
"min": 0.10242480000000001,
"max": 0.1973238,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.512124,
"min": 0.4293968,
"max": 0.9618960000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00013099752000000003,
"min": 0.00013099752000000003,
"max": 0.00486645762,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0006549876000000002,
"min": 0.0006549876000000002,
"max": 0.023098610400000004,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1711987810",
"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=SnowballTarget1-2 --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": "1711990076"
},
"total": 2265.935300367,
"count": 1,
"self": 0.6950925349997306,
"children": {
"run_training.setup": {
"total": 0.0494928829998571,
"count": 1,
"self": 0.0494928829998571
},
"TrainerController.start_learning": {
"total": 2265.1907149490003,
"count": 1,
"self": 2.5203987189806867,
"children": {
"TrainerController._reset_env": {
"total": 2.0649548219998906,
"count": 1,
"self": 2.0649548219998906
},
"TrainerController.advance": {
"total": 2260.366078167019,
"count": 90961,
"self": 1.223690008137055,
"children": {
"env_step": {
"total": 2259.142388158882,
"count": 90961,
"self": 1547.9900917887344,
"children": {
"SubprocessEnvManager._take_step": {
"total": 709.8495093980287,
"count": 90961,
"self": 6.71344353007953,
"children": {
"TorchPolicy.evaluate": {
"total": 703.1360658679491,
"count": 90961,
"self": 703.1360658679491
}
}
},
"workers": {
"total": 1.3027869721190655,
"count": 90961,
"self": 0.0,
"children": {
"worker_root": {
"total": 2259.662807122017,
"count": 90961,
"is_parallel": true,
"self": 1211.8170510369805,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002354731999730575,
"count": 1,
"is_parallel": true,
"self": 0.0006868690002193034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016678629995112715,
"count": 10,
"is_parallel": true,
"self": 0.0016678629995112715
}
}
},
"UnityEnvironment.step": {
"total": 0.03539436599976398,
"count": 1,
"is_parallel": true,
"self": 0.0006610240002373757,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039608499992027646,
"count": 1,
"is_parallel": true,
"self": 0.00039608499992027646
},
"communicator.exchange": {
"total": 0.03245250499958274,
"count": 1,
"is_parallel": true,
"self": 0.03245250499958274
},
"steps_from_proto": {
"total": 0.0018847520000235818,
"count": 1,
"is_parallel": true,
"self": 0.00036443599992708187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015203160000965,
"count": 10,
"is_parallel": true,
"self": 0.0015203160000965
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1047.8457560850366,
"count": 90960,
"is_parallel": true,
"self": 48.72161101503298,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.138740830963343,
"count": 90960,
"is_parallel": true,
"self": 25.138740830963343
},
"communicator.exchange": {
"total": 815.141583917075,
"count": 90960,
"is_parallel": true,
"self": 815.141583917075
},
"steps_from_proto": {
"total": 158.84382032196527,
"count": 90960,
"is_parallel": true,
"self": 28.866446926747358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 129.9773733952179,
"count": 909600,
"is_parallel": true,
"self": 129.9773733952179
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002771930003291345,
"count": 1,
"self": 0.0002771930003291345,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2226.6474361739615,
"count": 4046041,
"is_parallel": true,
"self": 82.48284153357645,
"children": {
"process_trajectory": {
"total": 1338.482187173383,
"count": 4046041,
"is_parallel": true,
"self": 1333.523541035383,
"children": {
"RLTrainer._checkpoint": {
"total": 4.958646137999949,
"count": 20,
"is_parallel": true,
"self": 4.958646137999949
}
}
},
"_update_policy": {
"total": 805.6824074670021,
"count": 91,
"is_parallel": true,
"self": 387.42922644004284,
"children": {
"TorchPPOOptimizer.update": {
"total": 418.2531810269593,
"count": 19085,
"is_parallel": true,
"self": 418.2531810269593
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2390060480001921,
"count": 1,
"self": 0.003964724000070419,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23504132400012168,
"count": 1,
"self": 0.23504132400012168
}
}
}
}
}
}
}