neopolita's picture
First Push
a687549
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5288203358650208,
"min": 0.5288203358650208,
"max": 1.5151692628860474,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15779.9990234375,
"min": 15779.9990234375,
"max": 45964.17578125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989909.0,
"min": 29952.0,
"max": 989909.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989909.0,
"min": 29952.0,
"max": 989909.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3662775158882141,
"min": -0.15239715576171875,
"max": 0.3662775158882141,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 96.697265625,
"min": -36.118125915527344,
"max": 96.697265625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.5751437544822693,
"min": -0.5751437544822693,
"max": 0.36084112524986267,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -151.83795166015625,
"min": -151.83795166015625,
"max": 85.51934814453125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06428432560780839,
"min": 0.06428432560780839,
"max": 0.07270600925005988,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.8999805585093175,
"min": 0.4836998495213746,
"max": 1.0694608458765218,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.040582089570567144,
"min": 0.0006213715776571657,
"max": 0.040582089570567144,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.56814925398794,
"min": 0.00869920208720032,
"max": 0.56814925398794,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.524997491700001e-06,
"min": 7.524997491700001e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010534996488380001,
"min": 0.00010534996488380001,
"max": 0.0036335605888131997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025083,
"min": 0.1025083,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4351162,
"min": 1.3886848,
"max": 2.6111868000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026057917000000007,
"min": 0.00026057917000000007,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003648108380000001,
"min": 0.003648108380000001,
"max": 0.12113756132,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010700717568397522,
"min": 0.010700717568397522,
"max": 0.4788675308227539,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1498100459575653,
"min": 0.1498100459575653,
"max": 3.3520727157592773,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 501.0,
"min": 501.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29559.0,
"min": 15984.0,
"max": 33528.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2955626916077176,
"min": -1.0000000521540642,
"max": 1.2955626916077176,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 76.43819880485535,
"min": -29.791601561009884,
"max": 76.43819880485535,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2955626916077176,
"min": -1.0000000521540642,
"max": 1.2955626916077176,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 76.43819880485535,
"min": -29.791601561009884,
"max": 76.43819880485535,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05596626703753195,
"min": 0.05596626703753195,
"max": 9.39550372492522,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.3020097552143852,
"min": 3.2560782405926147,
"max": 150.32805959880352,
"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": "1702420555",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702422693"
},
"total": 2137.746898523,
"count": 1,
"self": 0.49476743299965165,
"children": {
"run_training.setup": {
"total": 0.0800425439999799,
"count": 1,
"self": 0.0800425439999799
},
"TrainerController.start_learning": {
"total": 2137.172088546,
"count": 1,
"self": 1.4029924000205938,
"children": {
"TrainerController._reset_env": {
"total": 3.6532272360000206,
"count": 1,
"self": 3.6532272360000206
},
"TrainerController.advance": {
"total": 2132.0301477499793,
"count": 63430,
"self": 1.5027859939114023,
"children": {
"env_step": {
"total": 1481.4195344060572,
"count": 63430,
"self": 1342.352929343054,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.188628218036,
"count": 63430,
"self": 4.994861230056813,
"children": {
"TorchPolicy.evaluate": {
"total": 133.1937669879792,
"count": 62562,
"self": 133.1937669879792
}
}
},
"workers": {
"total": 0.8779768449671792,
"count": 63430,
"self": 0.0,
"children": {
"worker_root": {
"total": 2132.573743546062,
"count": 63430,
"is_parallel": true,
"self": 914.3390748910876,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025429529998746148,
"count": 1,
"is_parallel": true,
"self": 0.0007880090001890494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017549439996855654,
"count": 8,
"is_parallel": true,
"self": 0.0017549439996855654
}
}
},
"UnityEnvironment.step": {
"total": 0.0538288029999876,
"count": 1,
"is_parallel": true,
"self": 0.0006342500000755535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005205169998134807,
"count": 1,
"is_parallel": true,
"self": 0.0005205169998134807
},
"communicator.exchange": {
"total": 0.05083613600004355,
"count": 1,
"is_parallel": true,
"self": 0.05083613600004355
},
"steps_from_proto": {
"total": 0.001837900000055015,
"count": 1,
"is_parallel": true,
"self": 0.0003875419999985752,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014503580000564398,
"count": 8,
"is_parallel": true,
"self": 0.0014503580000564398
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1218.2346686549743,
"count": 63429,
"is_parallel": true,
"self": 35.42833293195781,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.777930432967878,
"count": 63429,
"is_parallel": true,
"self": 25.777930432967878
},
"communicator.exchange": {
"total": 1053.1434845069682,
"count": 63429,
"is_parallel": true,
"self": 1053.1434845069682
},
"steps_from_proto": {
"total": 103.88492078308036,
"count": 63429,
"is_parallel": true,
"self": 21.05859447112357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.82632631195679,
"count": 507432,
"is_parallel": true,
"self": 82.82632631195679
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 649.1078273500109,
"count": 63430,
"self": 2.736416825011247,
"children": {
"process_trajectory": {
"total": 133.2354430750015,
"count": 63430,
"self": 133.05984579000142,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17559728500009442,
"count": 2,
"self": 0.17559728500009442
}
}
},
"_update_policy": {
"total": 513.1359674499981,
"count": 455,
"self": 305.5017351620238,
"children": {
"TorchPPOOptimizer.update": {
"total": 207.63423228797433,
"count": 22776,
"self": 207.63423228797433
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2860000424552709e-06,
"count": 1,
"self": 1.2860000424552709e-06
},
"TrainerController._save_models": {
"total": 0.0857198740000058,
"count": 1,
"self": 0.0013787960001536703,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08434107799985213,
"count": 1,
"self": 0.08434107799985213
}
}
}
}
}
}
}