SwordAndTea's picture
First Push
386f146 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5006667375564575,
"min": 0.5006667375564575,
"max": 1.4548754692077637,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14971.9375,
"min": 14971.9375,
"max": 44135.1015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989921.0,
"min": 29873.0,
"max": 989921.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989921.0,
"min": 29873.0,
"max": 989921.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5018920302391052,
"min": -0.19968868792057037,
"max": 0.5317635536193848,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 137.51841735839844,
"min": -47.32621765136719,
"max": 146.2349853515625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.06620211154222488,
"min": -0.03641469031572342,
"max": 0.3632914423942566,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 18.139379501342773,
"min": -9.358575820922852,
"max": 87.55323791503906,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06893485906212368,
"min": 0.0656886096355843,
"max": 0.07237056800658638,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9650880268697316,
"min": 0.49866509403238585,
"max": 1.0736697093234397,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013988459238871221,
"min": 0.0007637713583586971,
"max": 0.014724883739461509,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1958384293441971,
"min": 0.01069279901702176,
"max": 0.2061483723524611,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.723918853964287e-06,
"min": 7.723918853964287e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010813486395550001,
"min": 0.00010813486395550001,
"max": 0.003632844189052,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10257460714285715,
"min": 0.10257460714285715,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4360445000000002,
"min": 1.3886848,
"max": 2.610948,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026720325357142865,
"min": 0.00026720325357142865,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037408455500000013,
"min": 0.0037408455500000013,
"max": 0.12111370520000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011288349516689777,
"min": 0.011288349516689777,
"max": 0.6304835081100464,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15803688764572144,
"min": 0.15803688764572144,
"max": 4.413384437561035,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 366.5595238095238,
"min": 366.5595238095238,
"max": 988.5,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30791.0,
"min": 16800.0,
"max": 33639.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6334404599453722,
"min": -0.9269500514492393,
"max": 1.6334404599453722,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 137.20899863541126,
"min": -29.662401646375656,
"max": 137.20899863541126,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6334404599453722,
"min": -0.9269500514492393,
"max": 1.6334404599453722,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 137.20899863541126,
"min": -29.662401646375656,
"max": 137.20899863541126,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.042898788198640216,
"min": 0.042898788198640216,
"max": 12.479517452857074,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.603498208685778,
"min": 3.5878758847684367,
"max": 212.15179669857025,
"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": "1729130326",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729133642"
},
"total": 3316.143853041,
"count": 1,
"self": 1.0378910049998922,
"children": {
"run_training.setup": {
"total": 0.07632395600012387,
"count": 1,
"self": 0.07632395600012387
},
"TrainerController.start_learning": {
"total": 3315.02963808,
"count": 1,
"self": 2.442568204915915,
"children": {
"TrainerController._reset_env": {
"total": 2.5442745909999758,
"count": 1,
"self": 2.5442745909999758
},
"TrainerController.advance": {
"total": 3309.9569149030835,
"count": 63750,
"self": 2.564213589044357,
"children": {
"env_step": {
"total": 2168.9835895880133,
"count": 63750,
"self": 1995.905864696041,
"children": {
"SubprocessEnvManager._take_step": {
"total": 171.59522008103227,
"count": 63750,
"self": 7.168106649044148,
"children": {
"TorchPolicy.evaluate": {
"total": 164.42711343198812,
"count": 62547,
"self": 164.42711343198812
}
}
},
"workers": {
"total": 1.4825048109400996,
"count": 63750,
"self": 0.0,
"children": {
"worker_root": {
"total": 3307.660760440974,
"count": 63750,
"is_parallel": true,
"self": 1502.8381912639293,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003529790999891702,
"count": 1,
"is_parallel": true,
"self": 0.0012397989999044512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002289991999987251,
"count": 8,
"is_parallel": true,
"self": 0.002289991999987251
}
}
},
"UnityEnvironment.step": {
"total": 0.06604240399997252,
"count": 1,
"is_parallel": true,
"self": 0.0007998690002750664,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005259129998194112,
"count": 1,
"is_parallel": true,
"self": 0.0005259129998194112
},
"communicator.exchange": {
"total": 0.06242339599998559,
"count": 1,
"is_parallel": true,
"self": 0.06242339599998559
},
"steps_from_proto": {
"total": 0.0022932259998924565,
"count": 1,
"is_parallel": true,
"self": 0.0006024279998655402,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016907980000269163,
"count": 8,
"is_parallel": true,
"self": 0.0016907980000269163
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1804.822569177045,
"count": 63749,
"is_parallel": true,
"self": 50.36031516607045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 30.959897247016897,
"count": 63749,
"is_parallel": true,
"self": 30.959897247016897
},
"communicator.exchange": {
"total": 1592.3979922560316,
"count": 63749,
"is_parallel": true,
"self": 1592.3979922560316
},
"steps_from_proto": {
"total": 131.104364507926,
"count": 63749,
"is_parallel": true,
"self": 28.6254266531148,
"children": {
"_process_rank_one_or_two_observation": {
"total": 102.47893785481119,
"count": 509992,
"is_parallel": true,
"self": 102.47893785481119
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1138.4091117260257,
"count": 63750,
"self": 4.664603062012475,
"children": {
"process_trajectory": {
"total": 173.2984058990071,
"count": 63750,
"self": 173.08032429500713,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21808160399996268,
"count": 2,
"self": 0.21808160399996268
}
}
},
"_update_policy": {
"total": 960.4461027650061,
"count": 455,
"self": 379.29040171796623,
"children": {
"TorchPPOOptimizer.update": {
"total": 581.1557010470399,
"count": 22770,
"self": 581.1557010470399
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0809999366756529e-06,
"count": 1,
"self": 1.0809999366756529e-06
},
"TrainerController._save_models": {
"total": 0.0858793000006699,
"count": 1,
"self": 0.0022929340002519893,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08358636600041791,
"count": 1,
"self": 0.08358636600041791
}
}
}
}
}
}
}