fearofknowledge's picture
First Push
925ef56 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9222623705863953,
"min": 0.8905576467514038,
"max": 2.4195728302001953,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 46017.203125,
"min": 44435.265625,
"max": 122217.4609375,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.249113082885742,
"min": 3.109697103500366,
"max": 14.337869644165039,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 14291.8603515625,
"min": 3084.819580078125,
"max": 14366.544921875,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.09983500301520608,
"min": 0.09671839776588924,
"max": 0.10136368295668531,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 2.29620506934974,
"min": 2.163602967777405,
"max": 2.331364708003762,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16211005654074853,
"min": 0.16080141655675181,
"max": 0.25907502464079896,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 3.7285313004372163,
"min": 3.698432580805292,
"max": 5.9587255667383765,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.00030000000000000003,
"min": 0.0003,
"max": 0.00030000000000000003,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.006900000000000001,
"min": 0.0066,
"max": 0.006900000000000001,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.2,
"min": 0.2,
"max": 0.2,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 4.6000000000000005,
"min": 4.4,
"max": 4.6000000000000005,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.11500000000000002,
"min": 0.11000000000000001,
"max": 0.11500000000000002,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 50347.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.849802371541504,
"min": 10.5,
"max": 27.889328063241106,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 7046.0,
"min": 2541.0,
"max": 7056.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.849802371541504,
"min": 10.5,
"max": 27.889328063241106,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 7046.0,
"min": 2541.0,
"max": 7056.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1730208662",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730209918"
},
"total": 1255.87081546,
"count": 1,
"self": 0.4302480360001937,
"children": {
"run_training.setup": {
"total": 0.05451974899983725,
"count": 1,
"self": 0.05451974899983725
},
"TrainerController.start_learning": {
"total": 1255.3860476749999,
"count": 1,
"self": 0.8485796220036264,
"children": {
"TrainerController._reset_env": {
"total": 4.7847301659999175,
"count": 1,
"self": 4.7847301659999175
},
"TrainerController.advance": {
"total": 1249.6453425609966,
"count": 45464,
"self": 0.8558500940384874,
"children": {
"env_step": {
"total": 750.2136684169845,
"count": 45464,
"self": 561.2537208630208,
"children": {
"SubprocessEnvManager._take_step": {
"total": 188.44190218499944,
"count": 45464,
"self": 3.0874929349893137,
"children": {
"TorchPolicy.evaluate": {
"total": 185.35440925001012,
"count": 45464,
"self": 185.35440925001012
}
}
},
"workers": {
"total": 0.5180453689642945,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1252.147069956013,
"count": 45464,
"is_parallel": true,
"self": 758.9605567290555,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00226167699997859,
"count": 1,
"is_parallel": true,
"self": 0.0006993060001150297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015623709998635604,
"count": 10,
"is_parallel": true,
"self": 0.0015623709998635604
}
}
},
"UnityEnvironment.step": {
"total": 0.03557854599989696,
"count": 1,
"is_parallel": true,
"self": 0.0006379300000389776,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000401834999820494,
"count": 1,
"is_parallel": true,
"self": 0.000401834999820494
},
"communicator.exchange": {
"total": 0.032411240000101316,
"count": 1,
"is_parallel": true,
"self": 0.032411240000101316
},
"steps_from_proto": {
"total": 0.0021275409999361727,
"count": 1,
"is_parallel": true,
"self": 0.00036599000009118754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017615509998449852,
"count": 10,
"is_parallel": true,
"self": 0.0017615509998449852
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 493.18651322695746,
"count": 45463,
"is_parallel": true,
"self": 24.475282738909073,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.043458734026672,
"count": 45463,
"is_parallel": true,
"self": 13.043458734026672
},
"communicator.exchange": {
"total": 377.3931636409643,
"count": 45463,
"is_parallel": true,
"self": 377.3931636409643
},
"steps_from_proto": {
"total": 78.27460811305741,
"count": 45463,
"is_parallel": true,
"self": 14.293080629048745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.981527484008666,
"count": 454630,
"is_parallel": true,
"self": 63.981527484008666
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 498.57582404997356,
"count": 45464,
"self": 1.0497659909981394,
"children": {
"process_trajectory": {
"total": 119.22277279797572,
"count": 45464,
"self": 119.01738107097572,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20539172700000563,
"count": 1,
"self": 0.20539172700000563
}
}
},
"_update_policy": {
"total": 378.3032852609997,
"count": 227,
"self": 105.62508455198781,
"children": {
"TorchPPOOptimizer.update": {
"total": 272.6782007090119,
"count": 23151,
"self": 272.6782007090119
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.919999683916103e-07,
"count": 1,
"self": 9.919999683916103e-07
},
"TrainerController._save_models": {
"total": 0.10739433399976406,
"count": 1,
"self": 0.0007819259994903405,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10661240800027372,
"count": 1,
"self": 0.10661240800027372
}
}
}
}
}
}
}