arminmrm93's picture
First Push
0fcbca6
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.0129324197769165,
"min": 0.7151864171028137,
"max": 1.4372490644454956,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 30339.353515625,
"min": 21421.263671875,
"max": 43600.38671875,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479945.0,
"min": 29962.0,
"max": 479945.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479945.0,
"min": 29962.0,
"max": 479945.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.011681661941111088,
"min": -0.13958127796649933,
"max": 0.011681661941111088,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 2.8620071411132812,
"min": -33.22034454345703,
"max": 2.8620071411132812,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.029486119747161865,
"min": 0.027405153959989548,
"max": 0.2600449323654175,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.224099159240723,
"min": 6.577237129211426,
"max": 62.41078186035156,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06801359974086783,
"min": 0.06488899509318131,
"max": 0.07553129586150316,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0202039961130176,
"min": 0.454548342968839,
"max": 1.0202039961130176,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005582945410846198,
"min": 0.0004580204897774796,
"max": 0.013711394003657378,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.08374418116269297,
"min": 0.004122184407997317,
"max": 0.09597975802560164,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.1051372982906668e-05,
"min": 2.1051372982906668e-05,
"max": 0.0002904759460318285,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0003157705947436,
"min": 0.0003157705947436,
"max": 0.0028159108613632,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10701709333333337,
"min": 0.10701709333333337,
"max": 0.19682531428571431,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.6052564000000005,
"min": 1.3777772000000001,
"max": 2.3386368,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007110076240000003,
"min": 0.0007110076240000003,
"max": 0.009682848897142856,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.010665114360000004,
"min": 0.010665114360000004,
"max": 0.09390981631999999,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0166071318089962,
"min": 0.0166071318089962,
"max": 0.3668909966945648,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2491069883108139,
"min": 0.23651857674121857,
"max": 2.568237066268921,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 819.2972972972973,
"min": 819.2972972972973,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30314.0,
"min": 16633.0,
"max": 32103.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.008843282187307204,
"min": -0.9999806972280625,
"max": -0.008843282187307204,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -0.3272014409303665,
"min": -31.998801663517952,
"max": -0.3272014409303665,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.008843282187307204,
"min": -0.9999806972280625,
"max": -0.008843282187307204,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -0.3272014409303665,
"min": -31.998801663517952,
"max": -0.3272014409303665,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.14314874204353908,
"min": 0.14314874204353908,
"max": 6.944004123482634,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.296503455610946,
"min": 5.093305759131908,
"max": 118.04807009920478,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687838129",
"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=My 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": "1687839173"
},
"total": 1044.217866708,
"count": 1,
"self": 0.47624675000020034,
"children": {
"run_training.setup": {
"total": 0.06405086899997059,
"count": 1,
"self": 0.06405086899997059
},
"TrainerController.start_learning": {
"total": 1043.677569089,
"count": 1,
"self": 0.6374927539934561,
"children": {
"TrainerController._reset_env": {
"total": 4.669657947000019,
"count": 1,
"self": 4.669657947000019
},
"TrainerController.advance": {
"total": 1038.2760054170064,
"count": 31581,
"self": 0.6822988709911897,
"children": {
"env_step": {
"total": 717.4053586640005,
"count": 31581,
"self": 661.9723847870174,
"children": {
"SubprocessEnvManager._take_step": {
"total": 55.04250034599863,
"count": 31581,
"self": 2.4061927760034223,
"children": {
"TorchPolicy.evaluate": {
"total": 52.63630756999521,
"count": 31315,
"self": 52.63630756999521
}
}
},
"workers": {
"total": 0.3904735309844227,
"count": 31581,
"self": 0.0,
"children": {
"worker_root": {
"total": 1041.3370702609918,
"count": 31581,
"is_parallel": true,
"self": 433.8246731850014,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004858667999997124,
"count": 1,
"is_parallel": true,
"self": 0.0035525630000279307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013061049999691932,
"count": 8,
"is_parallel": true,
"self": 0.0013061049999691932
}
}
},
"UnityEnvironment.step": {
"total": 0.047715159999938805,
"count": 1,
"is_parallel": true,
"self": 0.0005449319999115687,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004928690000269853,
"count": 1,
"is_parallel": true,
"self": 0.0004928690000269853
},
"communicator.exchange": {
"total": 0.044919184000036694,
"count": 1,
"is_parallel": true,
"self": 0.044919184000036694
},
"steps_from_proto": {
"total": 0.0017581749999635576,
"count": 1,
"is_parallel": true,
"self": 0.0003373679999185697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001420807000044988,
"count": 8,
"is_parallel": true,
"self": 0.001420807000044988
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 607.5123970759904,
"count": 31580,
"is_parallel": true,
"self": 16.701845790002267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.078513058997942,
"count": 31580,
"is_parallel": true,
"self": 11.078513058997942
},
"communicator.exchange": {
"total": 529.7543632010035,
"count": 31580,
"is_parallel": true,
"self": 529.7543632010035
},
"steps_from_proto": {
"total": 49.97767502598674,
"count": 31580,
"is_parallel": true,
"self": 9.611533107969194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.36614191801755,
"count": 252640,
"is_parallel": true,
"self": 40.36614191801755
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 320.1883478820149,
"count": 31581,
"self": 1.1167922179967036,
"children": {
"process_trajectory": {
"total": 52.848097843017285,
"count": 31581,
"self": 52.73577157901718,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11232626400010304,
"count": 1,
"self": 0.11232626400010304
}
}
},
"_update_policy": {
"total": 266.2234578210009,
"count": 209,
"self": 170.12687449899647,
"children": {
"TorchPPOOptimizer.update": {
"total": 96.09658332200445,
"count": 11427,
"self": 96.09658332200445
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1120000635855831e-06,
"count": 1,
"self": 1.1120000635855831e-06
},
"TrainerController._save_models": {
"total": 0.09441185899981974,
"count": 1,
"self": 0.0014307009998901776,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09298115799992956,
"count": 1,
"self": 0.09298115799992956
}
}
}
}
}
}
}