ppo-PyramidsRND / run_logs /timers.json
RajMoodley's picture
Pyramids Push
d4ff3c5
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.30178722739219666,
"min": 0.30178722739219666,
"max": 1.4943398237228394,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9014.98828125,
"min": 9014.98828125,
"max": 45332.29296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989988.0,
"min": 29917.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989988.0,
"min": 29917.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4012119174003601,
"min": -0.08763467520475388,
"max": 0.4648074805736542,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 107.9260025024414,
"min": -21.03232192993164,
"max": 125.96282958984375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014903792180120945,
"min": -0.00043203687528148293,
"max": 0.36814430356025696,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.009119987487793,
"min": -0.11492180824279785,
"max": 87.25019836425781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07180527635455929,
"min": 0.0653446257504581,
"max": 0.07296002953585903,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.00527386896383,
"min": 0.5709190825833416,
"max": 1.0544934211404586,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01487944497391715,
"min": 0.00020908917676045643,
"max": 0.01629616770670899,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2083122296348401,
"min": 0.0025090701211254772,
"max": 0.22814634789392588,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.22812616208572e-06,
"min": 7.22812616208572e-06,
"max": 0.0002952122640959125,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010119376626920007,
"min": 0.00010119376626920007,
"max": 0.003608629297123599,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10240934285714287,
"min": 0.10240934285714287,
"max": 0.1984040875,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4337308000000002,
"min": 1.4337308000000002,
"max": 2.5692214000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025069335142857165,
"min": 0.00025069335142857165,
"max": 0.009840568341249998,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035097069200000033,
"min": 0.0035097069200000033,
"max": 0.12029735235999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012552527710795403,
"min": 0.012545930221676826,
"max": 0.3690875172615051,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17573538422584534,
"min": 0.17564302682876587,
"max": 2.952700138092041,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 437.030303030303,
"min": 425.0869565217391,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28844.0,
"min": 15949.0,
"max": 32554.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4114181564161272,
"min": -0.9999750526621938,
"max": 1.4619571189795222,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 93.1535983234644,
"min": -31.9992016851902,
"max": 102.33699832856655,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4114181564161272,
"min": -0.9999750526621938,
"max": 1.4619571189795222,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 93.1535983234644,
"min": -31.9992016851902,
"max": 102.33699832856655,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05745910272239461,
"min": 0.05629999463515071,
"max": 7.611771716736257,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.792300779678044,
"min": 3.7720996405550977,
"max": 121.78834746778011,
"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": "1673419372",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673421318"
},
"total": 1946.658354826,
"count": 1,
"self": 0.4459034330002396,
"children": {
"run_training.setup": {
"total": 0.10591024999996534,
"count": 1,
"self": 0.10591024999996534
},
"TrainerController.start_learning": {
"total": 1946.106541143,
"count": 1,
"self": 1.1331669719650108,
"children": {
"TrainerController._reset_env": {
"total": 7.3896968310000375,
"count": 1,
"self": 7.3896968310000375
},
"TrainerController.advance": {
"total": 1937.495250138035,
"count": 63648,
"self": 1.1976458450124028,
"children": {
"env_step": {
"total": 1291.5079520640281,
"count": 63648,
"self": 1193.9535243140792,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.84119081398387,
"count": 63648,
"self": 4.02606766701831,
"children": {
"TorchPolicy.evaluate": {
"total": 92.81512314696556,
"count": 62568,
"self": 31.777580772948113,
"children": {
"TorchPolicy.sample_actions": {
"total": 61.03754237401745,
"count": 62568,
"self": 61.03754237401745
}
}
}
}
},
"workers": {
"total": 0.7132369359650284,
"count": 63648,
"self": 0.0,
"children": {
"worker_root": {
"total": 1942.8860493940012,
"count": 63648,
"is_parallel": true,
"self": 843.3478659630134,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0058971239999436875,
"count": 1,
"is_parallel": true,
"self": 0.0033798910000086835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002517232999935004,
"count": 8,
"is_parallel": true,
"self": 0.002517232999935004
}
}
},
"UnityEnvironment.step": {
"total": 0.04700631899993368,
"count": 1,
"is_parallel": true,
"self": 0.0004970920000459955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000451350999924216,
"count": 1,
"is_parallel": true,
"self": 0.000451350999924216
},
"communicator.exchange": {
"total": 0.04444766099993558,
"count": 1,
"is_parallel": true,
"self": 0.04444766099993558
},
"steps_from_proto": {
"total": 0.0016102150000278925,
"count": 1,
"is_parallel": true,
"self": 0.00044009200007621985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011701229999516727,
"count": 8,
"is_parallel": true,
"self": 0.0011701229999516727
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1099.5381834309878,
"count": 63647,
"is_parallel": true,
"self": 27.35988828103973,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.88752222503126,
"count": 63647,
"is_parallel": true,
"self": 21.88752222503126
},
"communicator.exchange": {
"total": 960.7505350559721,
"count": 63647,
"is_parallel": true,
"self": 960.7505350559721
},
"steps_from_proto": {
"total": 89.54023786894459,
"count": 63647,
"is_parallel": true,
"self": 20.74257085182387,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.79766701712072,
"count": 509176,
"is_parallel": true,
"self": 68.79766701712072
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 644.7896522289946,
"count": 63648,
"self": 2.2377694549985563,
"children": {
"process_trajectory": {
"total": 140.2128722849924,
"count": 63648,
"self": 140.0242834789923,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18858880600009797,
"count": 2,
"self": 0.18858880600009797
}
}
},
"_update_policy": {
"total": 502.3390104890036,
"count": 454,
"self": 195.30752380701233,
"children": {
"TorchPPOOptimizer.update": {
"total": 307.0314866819913,
"count": 22770,
"self": 307.0314866819913
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.879997039912269e-07,
"count": 1,
"self": 8.879997039912269e-07
},
"TrainerController._save_models": {
"total": 0.08842631400011669,
"count": 1,
"self": 0.0014527869998346432,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08697352700028205,
"count": 1,
"self": 0.08697352700028205
}
}
}
}
}
}
}