marianokamp's picture
Initial.
40783ce
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8318333029747009,
"min": 0.8318333029747009,
"max": 2.8611555099487305,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7942.34423828125,
"min": 7942.34423828125,
"max": 29301.09375,
"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": 12.920610427856445,
"min": 0.4934345483779907,
"max": 12.920610427856445,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.51904296875,
"min": 95.72630310058594,
"max": 2626.232421875,
"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.Losses.PolicyLoss.mean": {
"value": 0.07842128869906803,
"min": 0.06600426508392797,
"max": 0.07842128869906803,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3136851547962721,
"min": 0.2640170603357119,
"max": 0.3700784998934479,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19022299692619082,
"min": 0.14263795098568333,
"max": 0.29820073717365075,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7608919877047633,
"min": 0.5705518039427333,
"max": 1.3782440239892289,
"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.CumulativeReward.mean": {
"value": 25.65909090909091,
"min": 3.977272727272727,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 175.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.977272727272727,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 175.0,
"max": 1400.0,
"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": "1673610630",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673611193"
},
"total": 563.0615958659996,
"count": 1,
"self": 0.4769464959990728,
"children": {
"run_training.setup": {
"total": 0.13210754400006408,
"count": 1,
"self": 0.13210754400006408
},
"TrainerController.start_learning": {
"total": 562.4525418260005,
"count": 1,
"self": 0.9320694159705454,
"children": {
"TrainerController._reset_env": {
"total": 4.765636808999716,
"count": 1,
"self": 4.765636808999716
},
"TrainerController.advance": {
"total": 556.613797504031,
"count": 18201,
"self": 0.45250288204897515,
"children": {
"env_step": {
"total": 556.161294621982,
"count": 18201,
"self": 422.07088215695376,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.6209010000248,
"count": 18201,
"self": 2.115397059053521,
"children": {
"TorchPolicy.evaluate": {
"total": 131.50550394097127,
"count": 18201,
"self": 21.32008366990567,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.1854202710656,
"count": 18201,
"self": 110.1854202710656
}
}
}
}
},
"workers": {
"total": 0.4695114650035066,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 560.4977887199916,
"count": 18201,
"is_parallel": true,
"self": 246.7202260819795,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003362577999723726,
"count": 1,
"is_parallel": true,
"self": 0.0012073789998794382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021551989998442878,
"count": 10,
"is_parallel": true,
"self": 0.0021551989998442878
}
}
},
"UnityEnvironment.step": {
"total": 0.055405286000222986,
"count": 1,
"is_parallel": true,
"self": 0.0008787420006228785,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003155009999318281,
"count": 1,
"is_parallel": true,
"self": 0.0003155009999318281
},
"communicator.exchange": {
"total": 0.05189571099981549,
"count": 1,
"is_parallel": true,
"self": 0.05189571099981549
},
"steps_from_proto": {
"total": 0.0023153319998527877,
"count": 1,
"is_parallel": true,
"self": 0.0005376510002861323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017776809995666554,
"count": 10,
"is_parallel": true,
"self": 0.0017776809995666554
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 313.7775626380121,
"count": 18200,
"is_parallel": true,
"self": 12.656781160985702,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.048092114002429,
"count": 18200,
"is_parallel": true,
"self": 7.048092114002429
},
"communicator.exchange": {
"total": 250.67610107298924,
"count": 18200,
"is_parallel": true,
"self": 250.67610107298924
},
"steps_from_proto": {
"total": 43.39658829003474,
"count": 18200,
"is_parallel": true,
"self": 10.111540192942357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.285048097092385,
"count": 182000,
"is_parallel": true,
"self": 33.285048097092385
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.548799956362927e-05,
"count": 1,
"self": 6.548799956362927e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 551.8993654793662,
"count": 548193,
"is_parallel": true,
"self": 13.89122574331077,
"children": {
"process_trajectory": {
"total": 306.0629449130547,
"count": 548193,
"is_parallel": true,
"self": 304.81988905105436,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2430558620003467,
"count": 4,
"is_parallel": true,
"self": 1.2430558620003467
}
}
},
"_update_policy": {
"total": 231.94519482300075,
"count": 90,
"is_parallel": true,
"self": 58.854245216999516,
"children": {
"TorchPPOOptimizer.update": {
"total": 173.09094960600123,
"count": 4587,
"is_parallel": true,
"self": 173.09094960600123
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1409726089996184,
"count": 1,
"self": 0.0011775529992519296,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13979505600036646,
"count": 1,
"self": 0.13979505600036646
}
}
}
}
}
}
}