ppo-Pyramids / run_logs /timers.json
avoroshilov's picture
First Push
12cb7cf
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4486439526081085,
"min": 0.4486439526081085,
"max": 1.500130534172058,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13337.287109375,
"min": 13337.287109375,
"max": 45507.9609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989911.0,
"min": 29952.0,
"max": 989911.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989911.0,
"min": 29952.0,
"max": 989911.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5028076767921448,
"min": -0.1069408729672432,
"max": 0.5305113792419434,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 136.76368713378906,
"min": -25.772750854492188,
"max": 145.36012268066406,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.020727701485157013,
"min": 0.0067908549681305885,
"max": 0.4157068431377411,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.637934684753418,
"min": 1.8063673973083496,
"max": 98.52252197265625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06785624200064276,
"min": 0.06492135637984853,
"max": 0.07352641648288426,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0178436300096414,
"min": 0.5144432908417148,
"max": 1.056432743399865,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014293676298823103,
"min": 0.0007917397510501054,
"max": 0.016267027317856748,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21440514448234654,
"min": 0.01029261676365137,
"max": 0.24400540976785123,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.509797496766668e-06,
"min": 7.509797496766668e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011264696245150003,
"min": 0.00011264696245150003,
"max": 0.0033774493741835997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250323333333333,
"min": 0.10250323333333333,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375485,
"min": 1.3691136000000002,
"max": 2.4827042,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002600730100000001,
"min": 0.0002600730100000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003901095150000002,
"min": 0.003901095150000002,
"max": 0.11259905836000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01137490663677454,
"min": 0.011224797926843166,
"max": 0.5857481360435486,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17062360048294067,
"min": 0.15714716911315918,
"max": 4.100236892700195,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 363.5529411764706,
"min": 352.609756097561,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30902.0,
"min": 15984.0,
"max": 33891.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5187599834273844,
"min": -1.0000000521540642,
"max": 1.549790219108506,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 129.09459859132767,
"min": -32.000001668930054,
"max": 129.09459859132767,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5187599834273844,
"min": -1.0000000521540642,
"max": 1.549790219108506,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 129.09459859132767,
"min": -32.000001668930054,
"max": 129.09459859132767,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04272614125040812,
"min": 0.04272614125040812,
"max": 11.486394457519054,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.63172200628469,
"min": 3.4862456497212406,
"max": 183.78231132030487,
"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": "1678621881",
"python_version": "3.9.1 (default, Dec 11 2020, 14:32:07) \n[GCC 7.3.0]",
"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": "1.22.3",
"end_time_seconds": "1678626403"
},
"total": 4522.356154749,
"count": 1,
"self": 1.1448509249994459,
"children": {
"run_training.setup": {
"total": 0.08398882300025434,
"count": 1,
"self": 0.08398882300025434
},
"TrainerController.start_learning": {
"total": 4521.127315001,
"count": 1,
"self": 3.1001192581124997,
"children": {
"TrainerController._reset_env": {
"total": 2.6028202129996316,
"count": 1,
"self": 2.6028202129996316
},
"TrainerController.advance": {
"total": 4515.252865430888,
"count": 63851,
"self": 3.2663562667021324,
"children": {
"env_step": {
"total": 2781.4424821341163,
"count": 63851,
"self": 2596.648962685216,
"children": {
"SubprocessEnvManager._take_step": {
"total": 182.95496619396454,
"count": 63851,
"self": 9.370401570012291,
"children": {
"TorchPolicy.evaluate": {
"total": 173.58456462395225,
"count": 62563,
"self": 36.593050998914805,
"children": {
"TorchPolicy.sample_actions": {
"total": 136.99151362503744,
"count": 62563,
"self": 136.99151362503744
}
}
}
}
},
"workers": {
"total": 1.8385532549359596,
"count": 63851,
"self": 0.0,
"children": {
"worker_root": {
"total": 4510.057260151885,
"count": 63851,
"is_parallel": true,
"self": 2128.879884802893,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003745905999949173,
"count": 1,
"is_parallel": true,
"self": 0.001216596999711328,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002529309000237845,
"count": 8,
"is_parallel": true,
"self": 0.002529309000237845
}
}
},
"UnityEnvironment.step": {
"total": 0.17233178700007556,
"count": 1,
"is_parallel": true,
"self": 0.0007912440005384269,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0015949519997775496,
"count": 1,
"is_parallel": true,
"self": 0.0015949519997775496
},
"communicator.exchange": {
"total": 0.16772576099992875,
"count": 1,
"is_parallel": true,
"self": 0.16772576099992875
},
"steps_from_proto": {
"total": 0.0022198299998308357,
"count": 1,
"is_parallel": true,
"self": 0.000555820999579737,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016640090002510988,
"count": 8,
"is_parallel": true,
"self": 0.0016640090002510988
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2381.1773753489924,
"count": 63850,
"is_parallel": true,
"self": 48.618822645153614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 29.903474185962295,
"count": 63850,
"is_parallel": true,
"self": 29.903474185962295
},
"communicator.exchange": {
"total": 2143.497711304943,
"count": 63850,
"is_parallel": true,
"self": 2143.497711304943
},
"steps_from_proto": {
"total": 159.15736721293342,
"count": 63850,
"is_parallel": true,
"self": 41.948383643120906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 117.20898356981252,
"count": 510800,
"is_parallel": true,
"self": 117.20898356981252
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1730.5440270300692,
"count": 63851,
"self": 5.891089678031221,
"children": {
"process_trajectory": {
"total": 295.54915620804013,
"count": 63851,
"self": 295.1178867550411,
"children": {
"RLTrainer._checkpoint": {
"total": 0.431269452999004,
"count": 2,
"self": 0.431269452999004
}
}
},
"_update_policy": {
"total": 1429.1037811439978,
"count": 446,
"self": 434.73099960108766,
"children": {
"TorchPPOOptimizer.update": {
"total": 994.3727815429102,
"count": 22788,
"self": 994.3727815429102
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.1239993657218292e-06,
"count": 1,
"self": 2.1239993657218292e-06
},
"TrainerController._save_models": {
"total": 0.1715079750001678,
"count": 1,
"self": 0.0023439229998984956,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1691640520002693,
"count": 1,
"self": 0.1691640520002693
}
}
}
}
}
}
}