pcapp's picture
Initial commit
05f0225
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4725952446460724,
"min": 0.4725952446460724,
"max": 1.2996056079864502,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14117.365234375,
"min": 14117.365234375,
"max": 39424.8359375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989940.0,
"min": 29952.0,
"max": 989940.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989940.0,
"min": 29952.0,
"max": 989940.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4883023500442505,
"min": -0.09492082893848419,
"max": 0.5834103226661682,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 129.888427734375,
"min": -22.970840454101562,
"max": 162.771484375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03940414637327194,
"min": -0.14597351849079132,
"max": 0.7400143146514893,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 10.481502532958984,
"min": -35.763511657714844,
"max": 175.38339233398438,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06976189781395302,
"min": 0.06327683740657651,
"max": 0.07431628164905058,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9766665693953424,
"min": 0.505666141484559,
"max": 1.0769856056562561,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015832441045262876,
"min": 0.0009109044481605271,
"max": 0.02849275632098498,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22165417463368026,
"min": 0.011841757826086851,
"max": 0.4273913448147747,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.63961888206429e-06,
"min": 7.63961888206429e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010695466434890006,
"min": 0.00010695466434890006,
"max": 0.0034374915541694998,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254650714285715,
"min": 0.10254650714285715,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4356511,
"min": 1.3886848,
"max": 2.5277228,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002643960635714288,
"min": 0.0002643960635714288,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003701544890000003,
"min": 0.003701544890000003,
"max": 0.11458846695000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014689569361507893,
"min": 0.014689569361507893,
"max": 0.7128443121910095,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20565396547317505,
"min": 0.20565396547317505,
"max": 4.989910125732422,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 406.9066666666667,
"min": 328.4226804123711,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30518.0,
"min": 15984.0,
"max": 33099.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4864026407400768,
"min": -1.0000000521540642,
"max": 1.6303278144794642,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 111.48019805550575,
"min": -29.7202016338706,
"max": 158.14179800450802,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4864026407400768,
"min": -1.0000000521540642,
"max": 1.6303278144794642,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 111.48019805550575,
"min": -29.7202016338706,
"max": 158.14179800450802,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06182897205154101,
"min": 0.049824108537670574,
"max": 14.002368107438087,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.637172903865576,
"min": 4.44963545819337,
"max": 224.0378897190094,
"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": "1689613224",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1689615634"
},
"total": 2410.7040968399997,
"count": 1,
"self": 0.5751486119997935,
"children": {
"run_training.setup": {
"total": 0.04228537299991331,
"count": 1,
"self": 0.04228537299991331
},
"TrainerController.start_learning": {
"total": 2410.0866628549998,
"count": 1,
"self": 1.7769614530152467,
"children": {
"TrainerController._reset_env": {
"total": 4.193656403999967,
"count": 1,
"self": 4.193656403999967
},
"TrainerController.advance": {
"total": 2404.006778831985,
"count": 63861,
"self": 1.7646172789395678,
"children": {
"env_step": {
"total": 1735.817850027035,
"count": 63861,
"self": 1603.071162053086,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.70446668102568,
"count": 63861,
"self": 5.463323901068861,
"children": {
"TorchPolicy.evaluate": {
"total": 126.24114277995682,
"count": 62558,
"self": 126.24114277995682
}
}
},
"workers": {
"total": 1.0422212929233865,
"count": 63861,
"self": 0.0,
"children": {
"worker_root": {
"total": 2404.1244517579735,
"count": 63861,
"is_parallel": true,
"self": 934.1093226080218,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002765533999991021,
"count": 1,
"is_parallel": true,
"self": 0.0007606520002809702,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002004881999710051,
"count": 8,
"is_parallel": true,
"self": 0.002004881999710051
}
}
},
"UnityEnvironment.step": {
"total": 0.0536196140001266,
"count": 1,
"is_parallel": true,
"self": 0.0006289410000590578,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005181849999189581,
"count": 1,
"is_parallel": true,
"self": 0.0005181849999189581
},
"communicator.exchange": {
"total": 0.050389658000085547,
"count": 1,
"is_parallel": true,
"self": 0.050389658000085547
},
"steps_from_proto": {
"total": 0.0020828300000630406,
"count": 1,
"is_parallel": true,
"self": 0.0003773860003093432,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017054439997536974,
"count": 8,
"is_parallel": true,
"self": 0.0017054439997536974
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1470.0151291499517,
"count": 63860,
"is_parallel": true,
"self": 36.17976602508111,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.184592246951752,
"count": 63860,
"is_parallel": true,
"self": 25.184592246951752
},
"communicator.exchange": {
"total": 1291.288472920928,
"count": 63860,
"is_parallel": true,
"self": 1291.288472920928
},
"steps_from_proto": {
"total": 117.36229795699091,
"count": 63860,
"is_parallel": true,
"self": 23.60200475814395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.76029319884697,
"count": 510880,
"is_parallel": true,
"self": 93.76029319884697
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 666.4243115260101,
"count": 63861,
"self": 3.2303764649113873,
"children": {
"process_trajectory": {
"total": 120.45788710809961,
"count": 63861,
"self": 120.22731748509955,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2305696230000649,
"count": 2,
"self": 0.2305696230000649
}
}
},
"_update_policy": {
"total": 542.7360479529991,
"count": 456,
"self": 348.75468096099326,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.98136699200586,
"count": 22812,
"self": 193.98136699200586
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3300000318849925e-06,
"count": 1,
"self": 1.3300000318849925e-06
},
"TrainerController._save_models": {
"total": 0.10926483599996573,
"count": 1,
"self": 0.0015105850002328225,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1077542509997329,
"count": 1,
"self": 0.1077542509997329
}
}
}
}
}
}
}