ppo-Pyramids / run_logs /timers.json
andrea-silvi's picture
pyramids-first
097e0dd
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.09885845333337784,
"min": 0.09885845333337784,
"max": 1.391262173652649,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 2961.00830078125,
"min": 2961.00830078125,
"max": 42205.328125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989942.0,
"min": 29952.0,
"max": 989942.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989942.0,
"min": 29952.0,
"max": 989942.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.09300978481769562,
"min": -0.11049512028694153,
"max": -0.04772590473294258,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -22.41535758972168,
"min": -26.518829345703125,
"max": -11.50194263458252,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.7057044506072998,
"min": 0.3943696916103363,
"max": 0.7211557030677795,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 170.07476806640625,
"min": 93.46561431884766,
"max": 173.07736206054688,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06966624491625004,
"min": 0.06390519778727853,
"max": 0.07276667683861657,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9753274288275006,
"min": 0.5053176592062656,
"max": 1.0435171967746653,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.002272243285023804,
"min": 0.0012730152614169057,
"max": 0.01410997276765144,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.031811405990333254,
"min": 0.013503947598538854,
"max": 0.09876980937356009,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.468597510499998e-06,
"min": 7.468597510499998e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010456036514699997,
"min": 0.00010456036514699997,
"max": 0.0033823124725626,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248950000000001,
"min": 0.10248950000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4348530000000002,
"min": 1.3691136000000002,
"max": 2.5274373999999997,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002587010499999999,
"min": 0.0002587010499999999,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036218146999999986,
"min": 0.0036218146999999986,
"max": 0.11277099626,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.6952353119850159,
"min": 0.46431103348731995,
"max": 0.701970636844635,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 9.733294486999512,
"min": 3.286691665649414,
"max": 10.338406562805176,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 971.9677419354839,
"min": 942.2083333333334,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30131.0,
"min": 15984.0,
"max": 32978.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.9081290818510517,
"min": -1.0000000521540642,
"max": -0.5925652637429859,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -28.152001537382603,
"min": -32.000001668930054,
"max": -13.629001066088676,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.9081290818510517,
"min": -1.0000000521540642,
"max": -0.5925652637429859,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -28.152001537382603,
"min": -32.000001668930054,
"max": -13.629001066088676,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 6.750458623372739,
"min": 4.564700076938607,
"max": 12.862612821161747,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 209.26421732455492,
"min": 113.24149153381586,
"max": 219.23677159659564,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678110199",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1.22.4",
"end_time_seconds": "1678112313"
},
"total": 2113.926096401,
"count": 1,
"self": 0.44358649200012223,
"children": {
"run_training.setup": {
"total": 0.11608384800001659,
"count": 1,
"self": 0.11608384800001659
},
"TrainerController.start_learning": {
"total": 2113.366426061,
"count": 1,
"self": 1.235741714987853,
"children": {
"TrainerController._reset_env": {
"total": 10.123026120999953,
"count": 1,
"self": 10.123026120999953
},
"TrainerController.advance": {
"total": 2101.921326625012,
"count": 62964,
"self": 1.4148093849767065,
"children": {
"env_step": {
"total": 1353.883590047055,
"count": 62964,
"self": 1242.338978340114,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.73815874495813,
"count": 62964,
"self": 4.591770718939301,
"children": {
"TorchPolicy.evaluate": {
"total": 106.14638802601883,
"count": 62566,
"self": 36.07177086400759,
"children": {
"TorchPolicy.sample_actions": {
"total": 70.07461716201124,
"count": 62566,
"self": 70.07461716201124
}
}
}
}
},
"workers": {
"total": 0.8064529619829273,
"count": 62964,
"self": 0.0,
"children": {
"worker_root": {
"total": 2108.7938016910566,
"count": 62964,
"is_parallel": true,
"self": 977.7199052831074,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005293757000004007,
"count": 1,
"is_parallel": true,
"self": 0.003964434999943478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013293220000605288,
"count": 8,
"is_parallel": true,
"self": 0.0013293220000605288
}
}
},
"UnityEnvironment.step": {
"total": 0.04923415500002193,
"count": 1,
"is_parallel": true,
"self": 0.0005325830001083887,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005033899999489222,
"count": 1,
"is_parallel": true,
"self": 0.0005033899999489222
},
"communicator.exchange": {
"total": 0.046679495000034876,
"count": 1,
"is_parallel": true,
"self": 0.046679495000034876
},
"steps_from_proto": {
"total": 0.0015186869999297414,
"count": 1,
"is_parallel": true,
"self": 0.00037817099973835866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011405160001913828,
"count": 8,
"is_parallel": true,
"self": 0.0011405160001913828
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1131.0738964079492,
"count": 62963,
"is_parallel": true,
"self": 31.47343672595889,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.78740865404643,
"count": 62963,
"is_parallel": true,
"self": 22.78740865404643
},
"communicator.exchange": {
"total": 986.0875945519707,
"count": 62963,
"is_parallel": true,
"self": 986.0875945519707
},
"steps_from_proto": {
"total": 90.72545647597315,
"count": 62963,
"is_parallel": true,
"self": 21.305764869089444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 69.4196916068837,
"count": 503704,
"is_parallel": true,
"self": 69.4196916068837
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 746.6229271929803,
"count": 62964,
"self": 2.268821930978447,
"children": {
"process_trajectory": {
"total": 160.9588118200013,
"count": 62964,
"self": 160.72140422600137,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23740759399993294,
"count": 2,
"self": 0.23740759399993294
}
}
},
"_update_policy": {
"total": 583.3952934420006,
"count": 436,
"self": 234.2230539580039,
"children": {
"TorchPPOOptimizer.update": {
"total": 349.1722394839967,
"count": 22770,
"self": 349.1722394839967
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.359997991647106e-07,
"count": 1,
"self": 8.359997991647106e-07
},
"TrainerController._save_models": {
"total": 0.0863307640001949,
"count": 1,
"self": 0.0013738990005549567,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08495686499963995,
"count": 1,
"self": 0.08495686499963995
}
}
}
}
}
}
}