OldCrazyCoder's picture
First Push
a3499ee
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5655156970024109,
"min": 0.5352188944816589,
"max": 1.4919413328170776,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16947.375,
"min": 16142.201171875,
"max": 45259.53125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989980.0,
"min": 29952.0,
"max": 989980.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989980.0,
"min": 29952.0,
"max": 989980.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.36303845047950745,
"min": -0.0878649652004242,
"max": 0.36303845047950745,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 96.20519256591797,
"min": -21.08759117126465,
"max": 96.20519256591797,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.08588031679391861,
"min": -0.009479152970016003,
"max": 0.14567264914512634,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 22.758283615112305,
"min": -2.4456214904785156,
"max": 35.25278091430664,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06754774004867713,
"min": 0.06492313129370197,
"max": 0.07542332887117352,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.013216100730157,
"min": 0.520720394939417,
"max": 1.0609817898708997,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01665195623774909,
"min": 0.0005103791798642286,
"max": 0.01665195623774909,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24977934356623638,
"min": 0.0071453085180992,
"max": 0.24977934356623638,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.462177512639998e-06,
"min": 7.462177512639998e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011193266268959997,
"min": 0.00011193266268959997,
"max": 0.003508559330480299,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248736000000001,
"min": 0.10248736000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5373104000000002,
"min": 1.3886848,
"max": 2.5695197000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025848726400000004,
"min": 0.00025848726400000004,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038773089600000004,
"min": 0.0038773089600000004,
"max": 0.11697501802999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007264366373419762,
"min": 0.007006769068539143,
"max": 0.34919479489326477,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10896549373865128,
"min": 0.09809476882219315,
"max": 2.444363594055176,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 463.8333333333333,
"min": 463.8333333333333,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27830.0,
"min": 15984.0,
"max": 32544.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4027933022628227,
"min": -1.0000000521540642,
"max": 1.4027933022628227,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 84.16759813576937,
"min": -31.99760167300701,
"max": 84.16759813576937,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4027933022628227,
"min": -1.0000000521540642,
"max": 1.4027933022628227,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 84.16759813576937,
"min": -31.99760167300701,
"max": 84.16759813576937,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.035304877724108036,
"min": 0.035304877724108036,
"max": 7.358778215013444,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.118292663446482,
"min": 2.118292663446482,
"max": 117.74045144021511,
"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": "1692819767",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692822433"
},
"total": 2666.4073814060002,
"count": 1,
"self": 0.5331570369999099,
"children": {
"run_training.setup": {
"total": 0.04628197900001396,
"count": 1,
"self": 0.04628197900001396
},
"TrainerController.start_learning": {
"total": 2665.8279423900003,
"count": 1,
"self": 2.042060022001351,
"children": {
"TrainerController._reset_env": {
"total": 4.5058392529999765,
"count": 1,
"self": 4.5058392529999765
},
"TrainerController.advance": {
"total": 2659.174851710999,
"count": 63526,
"self": 1.95208606183769,
"children": {
"env_step": {
"total": 1913.5625128481552,
"count": 63526,
"self": 1770.1806308182586,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.20304180494895,
"count": 63526,
"self": 5.823308913978508,
"children": {
"TorchPolicy.evaluate": {
"total": 136.37973289097044,
"count": 62555,
"self": 136.37973289097044
}
}
},
"workers": {
"total": 1.1788402249476349,
"count": 63526,
"self": 0.0,
"children": {
"worker_root": {
"total": 2658.921204313011,
"count": 63526,
"is_parallel": true,
"self": 1036.368433785874,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002118878000146651,
"count": 1,
"is_parallel": true,
"self": 0.0006479069979832275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014709710021634237,
"count": 8,
"is_parallel": true,
"self": 0.0014709710021634237
}
}
},
"UnityEnvironment.step": {
"total": 0.05346846399970673,
"count": 1,
"is_parallel": true,
"self": 0.0006105349993958953,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005852220001543174,
"count": 1,
"is_parallel": true,
"self": 0.0005852220001543174
},
"communicator.exchange": {
"total": 0.050239262000104645,
"count": 1,
"is_parallel": true,
"self": 0.050239262000104645
},
"steps_from_proto": {
"total": 0.00203344500005187,
"count": 1,
"is_parallel": true,
"self": 0.0004306369992264081,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001602808000825462,
"count": 8,
"is_parallel": true,
"self": 0.001602808000825462
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1622.552770527137,
"count": 63525,
"is_parallel": true,
"self": 40.765856019924286,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 27.090755777071536,
"count": 63525,
"is_parallel": true,
"self": 27.090755777071536
},
"communicator.exchange": {
"total": 1428.1272758160476,
"count": 63525,
"is_parallel": true,
"self": 1428.1272758160476
},
"steps_from_proto": {
"total": 126.56888291409359,
"count": 63525,
"is_parallel": true,
"self": 25.85211406380131,
"children": {
"_process_rank_one_or_two_observation": {
"total": 100.71676885029228,
"count": 508200,
"is_parallel": true,
"self": 100.71676885029228
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 743.6602528010062,
"count": 63526,
"self": 3.6905059539694776,
"children": {
"process_trajectory": {
"total": 123.60193200104459,
"count": 63526,
"self": 123.23214812304377,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3697838780008169,
"count": 2,
"self": 0.3697838780008169
}
}
},
"_update_policy": {
"total": 616.3678148459921,
"count": 451,
"self": 402.39778880704125,
"children": {
"TorchPPOOptimizer.update": {
"total": 213.9700260389509,
"count": 22728,
"self": 213.9700260389509
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0009998732130043e-06,
"count": 1,
"self": 1.0009998732130043e-06
},
"TrainerController._save_models": {
"total": 0.10519040300005145,
"count": 1,
"self": 0.002100933999827248,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1030894690002242,
"count": 1,
"self": 0.1030894690002242
}
}
}
}
}
}
}