omarcevi's picture
First Push
557e95e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.27197420597076416,
"min": 0.27197420597076416,
"max": 1.450807809829712,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8207.09375,
"min": 8207.09375,
"max": 44011.70703125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989894.0,
"min": 29952.0,
"max": 989894.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989894.0,
"min": 29952.0,
"max": 989894.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3904078006744385,
"min": -0.09588117897510529,
"max": 0.46023547649383545,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 103.45806884765625,
"min": -23.203245162963867,
"max": 126.10452270507812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.01517522893846035,
"min": -0.018179776147007942,
"max": 0.31258684396743774,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.021435737609863,
"min": -4.817640781402588,
"max": 75.02084350585938,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07024715563221391,
"min": 0.0637954403267357,
"max": 0.07220254062128624,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9834601788509947,
"min": 0.4934720572765955,
"max": 1.0830381093192936,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014194586300401992,
"min": 0.0013566932382301803,
"max": 0.01685810578471449,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1987242082056279,
"min": 0.012210239144071622,
"max": 0.23601348098600286,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.626783172057146e-06,
"min": 7.626783172057146e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010677496440880004,
"min": 0.00010677496440880004,
"max": 0.0033761557746147994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254222857142858,
"min": 0.10254222857142858,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355912000000002,
"min": 1.3886848,
"max": 2.4424514000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002639686342857144,
"min": 0.0002639686342857144,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036955608800000013,
"min": 0.0036955608800000013,
"max": 0.11255598148000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01093342900276184,
"min": 0.01093342900276184,
"max": 0.44209352135658264,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15306800603866577,
"min": 0.15306800603866577,
"max": 3.0946545600891113,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 465.4,
"min": 398.54545454545456,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30251.0,
"min": 15984.0,
"max": 32259.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2575753620037666,
"min": -1.0000000521540642,
"max": 1.497519458656187,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 81.74239853024483,
"min": -29.89380170404911,
"max": 115.30899831652641,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2575753620037666,
"min": -1.0000000521540642,
"max": 1.497519458656187,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 81.74239853024483,
"min": -29.89380170404911,
"max": 115.30899831652641,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05311693820806865,
"min": 0.04830168172726166,
"max": 9.185996961779892,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.452600983524462,
"min": 3.452600983524462,
"max": 146.97595138847828,
"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": "1680152610",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680154716"
},
"total": 2105.9532954919996,
"count": 1,
"self": 0.48965282199969806,
"children": {
"run_training.setup": {
"total": 0.11049736699999357,
"count": 1,
"self": 0.11049736699999357
},
"TrainerController.start_learning": {
"total": 2105.353145303,
"count": 1,
"self": 1.4141570849960772,
"children": {
"TrainerController._reset_env": {
"total": 9.835601673999918,
"count": 1,
"self": 9.835601673999918
},
"TrainerController.advance": {
"total": 2094.009925565004,
"count": 63623,
"self": 1.4706091459988784,
"children": {
"env_step": {
"total": 1478.8191231319959,
"count": 63623,
"self": 1366.4810743159355,
"children": {
"SubprocessEnvManager._take_step": {
"total": 111.47653821699362,
"count": 63623,
"self": 4.936589322990017,
"children": {
"TorchPolicy.evaluate": {
"total": 106.5399488940036,
"count": 62577,
"self": 106.5399488940036
}
}
},
"workers": {
"total": 0.8615105990667189,
"count": 63623,
"self": 0.0,
"children": {
"worker_root": {
"total": 2100.224189334007,
"count": 63623,
"is_parallel": true,
"self": 854.2367647489727,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052291920000016034,
"count": 1,
"is_parallel": true,
"self": 0.0038448379999636018,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013843540000380017,
"count": 8,
"is_parallel": true,
"self": 0.0013843540000380017
}
}
},
"UnityEnvironment.step": {
"total": 0.07397987499996361,
"count": 1,
"is_parallel": true,
"self": 0.0005663649999405607,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045558299996173446,
"count": 1,
"is_parallel": true,
"self": 0.00045558299996173446
},
"communicator.exchange": {
"total": 0.07116186500002186,
"count": 1,
"is_parallel": true,
"self": 0.07116186500002186
},
"steps_from_proto": {
"total": 0.0017960620000394556,
"count": 1,
"is_parallel": true,
"self": 0.0003964500002666682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013996119997727874,
"count": 8,
"is_parallel": true,
"self": 0.0013996119997727874
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.9874245850342,
"count": 63622,
"is_parallel": true,
"self": 31.75602417401501,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.527674211023623,
"count": 63622,
"is_parallel": true,
"self": 23.527674211023623
},
"communicator.exchange": {
"total": 1095.2360318839987,
"count": 63622,
"is_parallel": true,
"self": 1095.2360318839987
},
"steps_from_proto": {
"total": 95.46769431599682,
"count": 63622,
"is_parallel": true,
"self": 20.514620582881776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.95307373311505,
"count": 508976,
"is_parallel": true,
"self": 74.95307373311505
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 613.720193287009,
"count": 63623,
"self": 2.5926146690072756,
"children": {
"process_trajectory": {
"total": 120.01126994599917,
"count": 63623,
"self": 119.79796288399893,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21330706200023997,
"count": 2,
"self": 0.21330706200023997
}
}
},
"_update_policy": {
"total": 491.11630867200256,
"count": 447,
"self": 312.3245192159783,
"children": {
"TorchPPOOptimizer.update": {
"total": 178.79178945602428,
"count": 22803,
"self": 178.79178945602428
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.720001798996236e-07,
"count": 1,
"self": 9.720001798996236e-07
},
"TrainerController._save_models": {
"total": 0.09346000699997603,
"count": 1,
"self": 0.0013591960000667314,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0921008109999093,
"count": 1,
"self": 0.0921008109999093
}
}
}
}
}
}
}