NishithR's picture
=First push
ec6cc96 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7371271848678589,
"min": 0.733815610408783,
"max": 2.8611226081848145,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7005.65673828125,
"min": 7005.65673828125,
"max": 29206.33984375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.239789009094238,
"min": 0.40697163343429565,
"max": 12.239789009094238,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2386.7587890625,
"min": 78.95249938964844,
"max": 2471.9267578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07259651292891553,
"min": 0.06369117179825017,
"max": 0.07325573497213304,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2903860517156621,
"min": 0.26588652188440715,
"max": 0.35827885537326115,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2048350725980366,
"min": 0.1414846804531693,
"max": 0.2932446552257912,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8193402903921464,
"min": 0.5659387218126772,
"max": 1.466223276128956,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.113636363636363,
"min": 3.75,
"max": 24.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1061.0,
"min": 165.0,
"max": 1321.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.113636363636363,
"min": 3.75,
"max": 24.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1061.0,
"min": 165.0,
"max": 1321.0,
"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": "1750668911",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750669333"
},
"total": 421.73220870600005,
"count": 1,
"self": 0.4345044389999657,
"children": {
"run_training.setup": {
"total": 0.023309909999966294,
"count": 1,
"self": 0.023309909999966294
},
"TrainerController.start_learning": {
"total": 421.2743943570001,
"count": 1,
"self": 0.3373467659984044,
"children": {
"TrainerController._reset_env": {
"total": 3.033174315999986,
"count": 1,
"self": 3.033174315999986
},
"TrainerController.advance": {
"total": 417.8238767040017,
"count": 18192,
"self": 0.3672902800154816,
"children": {
"env_step": {
"total": 300.05576796199455,
"count": 18192,
"self": 230.30813465099584,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.54259274999629,
"count": 18192,
"self": 1.2552856309962408,
"children": {
"TorchPolicy.evaluate": {
"total": 68.28730711900005,
"count": 18192,
"self": 68.28730711900005
}
}
},
"workers": {
"total": 0.20504056100241996,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.9225485259974,
"count": 18192,
"is_parallel": true,
"self": 217.64494272999048,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053533280000692685,
"count": 1,
"is_parallel": true,
"self": 0.0038665290001063113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014867989999629572,
"count": 10,
"is_parallel": true,
"self": 0.0014867989999629572
}
}
},
"UnityEnvironment.step": {
"total": 0.03492030999996132,
"count": 1,
"is_parallel": true,
"self": 0.0005725150000444046,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004153649999807385,
"count": 1,
"is_parallel": true,
"self": 0.0004153649999807385
},
"communicator.exchange": {
"total": 0.03216899699998521,
"count": 1,
"is_parallel": true,
"self": 0.03216899699998521
},
"steps_from_proto": {
"total": 0.0017634329999509646,
"count": 1,
"is_parallel": true,
"self": 0.0003442639998638697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001419169000087095,
"count": 10,
"is_parallel": true,
"self": 0.001419169000087095
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.27760579600692,
"count": 18191,
"is_parallel": true,
"self": 9.6485372189984,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.401058324999667,
"count": 18191,
"is_parallel": true,
"self": 5.401058324999667
},
"communicator.exchange": {
"total": 155.48683462599706,
"count": 18191,
"is_parallel": true,
"self": 155.48683462599706
},
"steps_from_proto": {
"total": 31.741175626011795,
"count": 18191,
"is_parallel": true,
"self": 5.703468964052149,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.037706661959646,
"count": 181910,
"is_parallel": true,
"self": 26.037706661959646
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.40081846199166,
"count": 18192,
"self": 0.4263227799984861,
"children": {
"process_trajectory": {
"total": 25.942031823993943,
"count": 18192,
"self": 25.5366407329941,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40539109099984216,
"count": 4,
"self": 0.40539109099984216
}
}
},
"_update_policy": {
"total": 91.03246385799923,
"count": 90,
"self": 37.41943751800204,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.61302633999719,
"count": 4587,
"self": 53.61302633999719
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.021000116452342e-06,
"count": 1,
"self": 1.021000116452342e-06
},
"TrainerController._save_models": {
"total": 0.07999554999992142,
"count": 1,
"self": 0.0008327880000251753,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07916276199989625,
"count": 1,
"self": 0.07916276199989625
}
}
}
}
}
}
}