gg232's picture
First Push
9875efa verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.28174272179603577,
"min": 0.28011032938957214,
"max": 1.4859033823013306,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8420.7265625,
"min": 8420.7265625,
"max": 45076.36328125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989948.0,
"min": 29952.0,
"max": 989948.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989948.0,
"min": 29952.0,
"max": 989948.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.49254047870635986,
"min": -0.11336362361907959,
"max": 0.5747332572937012,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 133.4784698486328,
"min": -27.547361373901367,
"max": 158.62637329101562,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.03987506404519081,
"min": -0.03987506404519081,
"max": 0.23863284289836884,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -10.806142807006836,
"min": -10.806142807006836,
"max": 57.9877815246582,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06760489051313406,
"min": 0.06517817362780785,
"max": 0.07378056358556839,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9464684671838769,
"min": 0.5094086680353562,
"max": 1.106708453783526,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01509752955081196,
"min": 0.00010303390098127842,
"max": 0.01582847727722111,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21136541371136744,
"min": 0.001442474613737898,
"max": 0.2374271591583167,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.288168999214284e-06,
"min": 7.288168999214284e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010203436598899998,
"min": 0.00010203436598899998,
"max": 0.0033273204908931993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10242935714285716,
"min": 0.10242935714285716,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340110000000001,
"min": 1.3886848,
"max": 2.4827304000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025269277857142857,
"min": 0.00025269277857142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035376989,
"min": 0.0035376989,
"max": 0.11091976932,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012720011174678802,
"min": 0.012503212317824364,
"max": 0.38708963990211487,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17808015644550323,
"min": 0.17808015644550323,
"max": 2.709627389907837,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 376.11538461538464,
"min": 338.32183908045977,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29337.0,
"min": 15984.0,
"max": 33377.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4691662042365445,
"min": -1.0000000521540642,
"max": 1.5281863482668996,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 113.12579772621393,
"min": -30.534001745283604,
"max": 134.48039864748716,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4691662042365445,
"min": -1.0000000521540642,
"max": 1.5281863482668996,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 113.12579772621393,
"min": -30.534001745283604,
"max": 134.48039864748716,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04834666034314848,
"min": 0.04392654401619273,
"max": 7.144515371881425,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.722692846422433,
"min": 3.722692846422433,
"max": 114.3122459501028,
"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": "1719118703",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719120969"
},
"total": 2265.5771257630004,
"count": 1,
"self": 0.4783787350006605,
"children": {
"run_training.setup": {
"total": 0.049976359999845954,
"count": 1,
"self": 0.049976359999845954
},
"TrainerController.start_learning": {
"total": 2265.0487706679996,
"count": 1,
"self": 1.3893871499944908,
"children": {
"TrainerController._reset_env": {
"total": 2.225228308999931,
"count": 1,
"self": 2.225228308999931
},
"TrainerController.advance": {
"total": 2261.345973422005,
"count": 63771,
"self": 1.482982694997645,
"children": {
"env_step": {
"total": 1613.204221255976,
"count": 63771,
"self": 1474.0600900689633,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.29687570401484,
"count": 63771,
"self": 4.872169382026641,
"children": {
"TorchPolicy.evaluate": {
"total": 133.4247063219882,
"count": 62559,
"self": 133.4247063219882
}
}
},
"workers": {
"total": 0.8472554829979799,
"count": 63771,
"self": 0.0,
"children": {
"worker_root": {
"total": 2259.7710304620064,
"count": 63771,
"is_parallel": true,
"self": 911.8509904069858,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021624090002205776,
"count": 1,
"is_parallel": true,
"self": 0.0006482300000243413,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015141790001962363,
"count": 8,
"is_parallel": true,
"self": 0.0015141790001962363
}
}
},
"UnityEnvironment.step": {
"total": 0.05139703199984069,
"count": 1,
"is_parallel": true,
"self": 0.0006580739998298668,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005559380001614045,
"count": 1,
"is_parallel": true,
"self": 0.0005559380001614045
},
"communicator.exchange": {
"total": 0.048271050000039395,
"count": 1,
"is_parallel": true,
"self": 0.048271050000039395
},
"steps_from_proto": {
"total": 0.001911969999810026,
"count": 1,
"is_parallel": true,
"self": 0.0003993849998096266,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015125850000003993,
"count": 8,
"is_parallel": true,
"self": 0.0015125850000003993
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1347.9200400550205,
"count": 63770,
"is_parallel": true,
"self": 34.802773920918526,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.280796956051518,
"count": 63770,
"is_parallel": true,
"self": 25.280796956051518
},
"communicator.exchange": {
"total": 1182.714192277075,
"count": 63770,
"is_parallel": true,
"self": 1182.714192277075
},
"steps_from_proto": {
"total": 105.12227690097552,
"count": 63770,
"is_parallel": true,
"self": 21.55481556799532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.5674613329802,
"count": 510160,
"is_parallel": true,
"self": 83.5674613329802
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 646.6587694710313,
"count": 63771,
"self": 2.6484116490901215,
"children": {
"process_trajectory": {
"total": 133.02412955893624,
"count": 63771,
"self": 132.80638338093604,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2177461780001977,
"count": 2,
"self": 0.2177461780001977
}
}
},
"_update_policy": {
"total": 510.98622826300493,
"count": 452,
"self": 302.89810066302834,
"children": {
"TorchPPOOptimizer.update": {
"total": 208.0881275999766,
"count": 22839,
"self": 208.0881275999766
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1679999261104967e-06,
"count": 1,
"self": 1.1679999261104967e-06
},
"TrainerController._save_models": {
"total": 0.0881806190000134,
"count": 1,
"self": 0.0014196110000739282,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08676100799993947,
"count": 1,
"self": 0.08676100799993947
}
}
}
}
}
}
}