shubhamagarwal92's picture
First Push
4b39841
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5484640002250671,
"min": 0.5444471836090088,
"max": 1.4419053792953491,
"count": 39
},
"Pyramids.Policy.Entropy.sum": {
"value": 16646.978515625,
"min": 16098.21484375,
"max": 43741.640625,
"count": 39
},
"Pyramids.Step.mean": {
"value": 1169891.0,
"min": 29952.0,
"max": 1169891.0,
"count": 39
},
"Pyramids.Step.sum": {
"value": 1169891.0,
"min": 29952.0,
"max": 1169891.0,
"count": 39
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6045730113983154,
"min": -0.09137479215860367,
"max": 0.6045730113983154,
"count": 39
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 168.0712890625,
"min": -21.929950714111328,
"max": 168.0712890625,
"count": 39
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004872982390224934,
"min": -0.018107283860445023,
"max": 0.3325161337852478,
"count": 39
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.354689121246338,
"min": -4.508713722229004,
"max": 78.80632019042969,
"count": 39
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0664657416509064,
"min": 0.06623878747408073,
"max": 0.07487294574032398,
"count": 39
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9305203831126895,
"min": 0.47167451753620265,
"max": 1.0668286626557044,
"count": 39
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012022044671880713,
"min": 0.00024274623953204633,
"max": 0.013534672958057317,
"count": 39
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16830862540633,
"min": 0.002184716155788417,
"max": 0.18948542141280245,
"count": 39
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00018458830989914762,
"min": 0.00018458830989914762,
"max": 0.00029838354339596195,
"count": 39
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0025842363385880666,
"min": 0.0020691136102954665,
"max": 0.003927589490803533,
"count": 39
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.16152942380952381,
"min": 0.16152942380952381,
"max": 0.19946118095238097,
"count": 39
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.2614119333333336,
"min": 1.3897045333333333,
"max": 2.767542666666667,
"count": 39
},
"Pyramids.Policy.Beta.mean": {
"value": 0.006156789438571429,
"min": 0.006156789438571429,
"max": 0.009946171977142856,
"count": 39
},
"Pyramids.Policy.Beta.sum": {
"value": 0.08619505214,
"min": 0.06897148288,
"max": 0.13092872702,
"count": 39
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007189449388533831,
"min": 0.007189449388533831,
"max": 0.45454785227775574,
"count": 39
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1006522923707962,
"min": 0.1006522923707962,
"max": 3.1818349361419678,
"count": 39
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 359.1190476190476,
"min": 347.6941176470588,
"max": 999.0,
"count": 39
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30166.0,
"min": 15984.0,
"max": 33437.0,
"count": 39
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5967858690549346,
"min": -1.0000000521540642,
"max": 1.6017880804304565,
"count": 39
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 135.72679886966944,
"min": -32.000001668930054,
"max": 135.72679886966944,
"count": 39
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5967858690549346,
"min": -1.0000000521540642,
"max": 1.6017880804304565,
"count": 39
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 135.72679886966944,
"min": -32.000001668930054,
"max": 135.72679886966944,
"count": 39
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.026626146463668728,
"min": 0.026626146463668728,
"max": 9.675345174968243,
"count": 39
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.263222449411842,
"min": 2.2023993528273422,
"max": 154.80552279949188,
"count": 39
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 39
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 39
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691267341",
"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=PyramidsTraining --no-graphics",
"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": "1691269842"
},
"total": 2501.17886549,
"count": 1,
"self": 0.3425878510001894,
"children": {
"run_training.setup": {
"total": 0.042375042000003305,
"count": 1,
"self": 0.042375042000003305
},
"TrainerController.start_learning": {
"total": 2500.793902597,
"count": 1,
"self": 1.5742190939326974,
"children": {
"TrainerController._reset_env": {
"total": 6.578324382000005,
"count": 1,
"self": 6.578324382000005
},
"TrainerController.advance": {
"total": 2492.4481669730676,
"count": 75489,
"self": 1.5726601750106965,
"children": {
"env_step": {
"total": 1730.37912666406,
"count": 75489,
"self": 1603.2431594880698,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.18898895500115,
"count": 75489,
"self": 5.605004287951033,
"children": {
"TorchPolicy.evaluate": {
"total": 120.58398466705012,
"count": 74154,
"self": 120.58398466705012
}
}
},
"workers": {
"total": 0.9469782209892514,
"count": 75488,
"self": 0.0,
"children": {
"worker_root": {
"total": 2495.093263823983,
"count": 75488,
"is_parallel": true,
"self": 1026.1639857730001,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005645235999963916,
"count": 1,
"is_parallel": true,
"self": 0.004168082999910894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001477153000053022,
"count": 8,
"is_parallel": true,
"self": 0.001477153000053022
}
}
},
"UnityEnvironment.step": {
"total": 0.04847209299998667,
"count": 1,
"is_parallel": true,
"self": 0.0005576840000003358,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046070400003372924,
"count": 1,
"is_parallel": true,
"self": 0.00046070400003372924
},
"communicator.exchange": {
"total": 0.04555765899999642,
"count": 1,
"is_parallel": true,
"self": 0.04555765899999642
},
"steps_from_proto": {
"total": 0.0018960459999561863,
"count": 1,
"is_parallel": true,
"self": 0.0003780639999035884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015179820000525979,
"count": 8,
"is_parallel": true,
"self": 0.0015179820000525979
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1468.9292780509827,
"count": 75487,
"is_parallel": true,
"self": 40.239576631993714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.434285032958428,
"count": 75487,
"is_parallel": true,
"self": 28.434285032958428
},
"communicator.exchange": {
"total": 1272.3524955699977,
"count": 75487,
"is_parallel": true,
"self": 1272.3524955699977
},
"steps_from_proto": {
"total": 127.90292081603286,
"count": 75487,
"is_parallel": true,
"self": 25.179085886051723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 102.72383492998114,
"count": 603896,
"is_parallel": true,
"self": 102.72383492998114
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 760.4963801339968,
"count": 75488,
"self": 3.039973433006594,
"children": {
"process_trajectory": {
"total": 131.6989825179927,
"count": 75488,
"self": 131.44131541099262,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25766710700008844,
"count": 2,
"self": 0.25766710700008844
}
}
},
"_update_policy": {
"total": 625.7574241829975,
"count": 529,
"self": 410.20386645699745,
"children": {
"TorchPPOOptimizer.update": {
"total": 215.55355772600007,
"count": 27081,
"self": 215.55355772600007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7449997358198743e-06,
"count": 1,
"self": 1.7449997358198743e-06
},
"TrainerController._save_models": {
"total": 0.1931904029997895,
"count": 1,
"self": 0.002089422999688395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19110098000010112,
"count": 1,
"self": 0.19110098000010112
}
}
}
}
}
}
}