Pavan132's picture
First Push
25c1b72 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7621527314186096,
"min": 0.7271846532821655,
"max": 2.8409476280212402,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7243.49951171875,
"min": 6988.46728515625,
"max": 29000.39453125,
"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": 12.809986114501953,
"min": 0.3832630217075348,
"max": 12.809986114501953,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2497.947265625,
"min": 74.35302734375,
"max": 2578.47509765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06143592272579268,
"min": 0.06007642580619836,
"max": 0.074324370264167,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24574369090317072,
"min": 0.24030570322479344,
"max": 0.371621851320835,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18076150495485932,
"min": 0.1259479550119745,
"max": 0.3158315928543315,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7230460198194373,
"min": 0.503791820047898,
"max": 1.4421960176790463,
"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": 26.045454545454547,
"min": 3.7045454545454546,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1146.0,
"min": 163.0,
"max": 1374.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.045454545454547,
"min": 3.7045454545454546,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1146.0,
"min": 163.0,
"max": 1374.0,
"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": "1739952616",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739953040"
},
"total": 424.72856548999994,
"count": 1,
"self": 0.44277325500002007,
"children": {
"run_training.setup": {
"total": 0.02359477599998172,
"count": 1,
"self": 0.02359477599998172
},
"TrainerController.start_learning": {
"total": 424.26219745899994,
"count": 1,
"self": 0.34529044302530565,
"children": {
"TrainerController._reset_env": {
"total": 3.0778374740000345,
"count": 1,
"self": 3.0778374740000345
},
"TrainerController.advance": {
"total": 420.7499724829745,
"count": 18192,
"self": 0.35622768600637755,
"children": {
"env_step": {
"total": 296.9184383779857,
"count": 18192,
"self": 225.57221837702377,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.13963250299071,
"count": 18192,
"self": 1.258999351987086,
"children": {
"TorchPolicy.evaluate": {
"total": 69.88063315100362,
"count": 18192,
"self": 69.88063315100362
}
}
},
"workers": {
"total": 0.20658749797121345,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 422.7499407409948,
"count": 18192,
"is_parallel": true,
"self": 224.99728764998804,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0067154599998957565,
"count": 1,
"is_parallel": true,
"self": 0.005207332000054521,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015081279998412356,
"count": 10,
"is_parallel": true,
"self": 0.0015081279998412356
}
}
},
"UnityEnvironment.step": {
"total": 0.034256960999982766,
"count": 1,
"is_parallel": true,
"self": 0.0005801580000479589,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003782300000239047,
"count": 1,
"is_parallel": true,
"self": 0.0003782300000239047
},
"communicator.exchange": {
"total": 0.03143472499982636,
"count": 1,
"is_parallel": true,
"self": 0.03143472499982636
},
"steps_from_proto": {
"total": 0.0018638480000845448,
"count": 1,
"is_parallel": true,
"self": 0.00036514700013867696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014987009999458678,
"count": 10,
"is_parallel": true,
"self": 0.0014987009999458678
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.75265309100678,
"count": 18191,
"is_parallel": true,
"self": 9.371735718034188,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.20750841999552,
"count": 18191,
"is_parallel": true,
"self": 5.20750841999552
},
"communicator.exchange": {
"total": 152.85886735298118,
"count": 18191,
"is_parallel": true,
"self": 152.85886735298118
},
"steps_from_proto": {
"total": 30.31454159999589,
"count": 18191,
"is_parallel": true,
"self": 5.375248709003472,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.93929289099242,
"count": 181910,
"is_parallel": true,
"self": 24.93929289099242
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.47530641898243,
"count": 18192,
"self": 0.43802883098237544,
"children": {
"process_trajectory": {
"total": 26.610346049998725,
"count": 18192,
"self": 26.0233169419987,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5870291080000243,
"count": 4,
"self": 0.5870291080000243
}
}
},
"_update_policy": {
"total": 96.42693153800133,
"count": 90,
"self": 38.42482741700155,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.002104120999775,
"count": 4587,
"self": 58.002104120999775
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.880001587385777e-07,
"count": 1,
"self": 8.880001587385777e-07
},
"TrainerController._save_models": {
"total": 0.08909617099993739,
"count": 1,
"self": 0.0009363389999634819,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0881598319999739,
"count": 1,
"self": 0.0881598319999739
}
}
}
}
}
}
}