ppo-Huggy / run_logs /timers.json
rjhuang's picture
Huggy
3117af6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3968043327331543,
"min": 1.3968043327331543,
"max": 1.425832748413086,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70629.4140625,
"min": 68555.59375,
"max": 77483.84375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.9204152249135,
"min": 77.92259083728278,
"max": 407.4715447154472,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49084.0,
"min": 48863.0,
"max": 50154.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999970.0,
"min": 49508.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999970.0,
"min": 49508.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.447861433029175,
"min": 0.061599232256412506,
"max": 2.491074800491333,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1414.8638916015625,
"min": 7.515106201171875,
"max": 1514.5733642578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.817676481130214,
"min": 1.8763311251265105,
"max": 3.9734802481663576,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2206.6170060932636,
"min": 228.91239726543427,
"max": 2390.924550950527,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.817676481130214,
"min": 1.8763311251265105,
"max": 3.9734802481663576,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2206.6170060932636,
"min": 228.91239726543427,
"max": 2390.924550950527,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013581255577173578,
"min": 0.013581255577173578,
"max": 0.020184165935885783,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.040743766731520734,
"min": 0.027215441597945755,
"max": 0.06055249780765735,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0570649401181274,
"min": 0.022450839169323444,
"max": 0.06206719589730104,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1711948203543822,
"min": 0.04490167833864689,
"max": 0.1770572703331709,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6581487806500136e-06,
"min": 3.6581487806500136e-06,
"max": 0.00029528985157004995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.097444634195004e-05,
"min": 1.097444634195004e-05,
"max": 0.0008440600686466499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121935000000003,
"min": 0.10121935000000003,
"max": 0.19842995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30365805000000007,
"min": 0.20757475000000003,
"max": 0.5813533500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.084556500000021e-05,
"min": 7.084556500000021e-05,
"max": 0.004921654505,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021253669500000065,
"min": 0.00021253669500000065,
"max": 0.014069532164999999,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740208047",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740210548"
},
"total": 2501.594950193,
"count": 1,
"self": 0.8068600169999627,
"children": {
"run_training.setup": {
"total": 0.023167632999957277,
"count": 1,
"self": 0.023167632999957277
},
"TrainerController.start_learning": {
"total": 2500.764922543,
"count": 1,
"self": 4.592773498959559,
"children": {
"TrainerController._reset_env": {
"total": 3.2743010980000236,
"count": 1,
"self": 3.2743010980000236
},
"TrainerController.advance": {
"total": 2492.71318819504,
"count": 232590,
"self": 4.860148604965161,
"children": {
"env_step": {
"total": 2000.6224676670163,
"count": 232590,
"self": 1569.4584660870014,
"children": {
"SubprocessEnvManager._take_step": {
"total": 428.3574301659735,
"count": 232590,
"self": 16.444398606986624,
"children": {
"TorchPolicy.evaluate": {
"total": 411.91303155898686,
"count": 223054,
"self": 411.91303155898686
}
}
},
"workers": {
"total": 2.8065714140414,
"count": 232590,
"self": 0.0,
"children": {
"worker_root": {
"total": 2492.5811348480056,
"count": 232590,
"is_parallel": true,
"self": 1212.6050116869842,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001026609000064127,
"count": 1,
"is_parallel": true,
"self": 0.00022895799997968425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007976510000844428,
"count": 2,
"is_parallel": true,
"self": 0.0007976510000844428
}
}
},
"UnityEnvironment.step": {
"total": 0.04867140700002892,
"count": 1,
"is_parallel": true,
"self": 0.00036916600004133215,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032179000004362024,
"count": 1,
"is_parallel": true,
"self": 0.00032179000004362024
},
"communicator.exchange": {
"total": 0.047275302999992164,
"count": 1,
"is_parallel": true,
"self": 0.047275302999992164
},
"steps_from_proto": {
"total": 0.0007051479999518051,
"count": 1,
"is_parallel": true,
"self": 0.00021184499996707018,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004933029999847349,
"count": 2,
"is_parallel": true,
"self": 0.0004933029999847349
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1279.9761231610214,
"count": 232589,
"is_parallel": true,
"self": 38.09638400886706,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.58459284409412,
"count": 232589,
"is_parallel": true,
"self": 82.58459284409412
},
"communicator.exchange": {
"total": 1068.9714802400144,
"count": 232589,
"is_parallel": true,
"self": 1068.9714802400144
},
"steps_from_proto": {
"total": 90.3236660680459,
"count": 232589,
"is_parallel": true,
"self": 33.57080967299203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.75285639505387,
"count": 465178,
"is_parallel": true,
"self": 56.75285639505387
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.2305719230585,
"count": 232590,
"self": 6.755958135054698,
"children": {
"process_trajectory": {
"total": 169.38104999900702,
"count": 232590,
"self": 167.80414390300712,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5769060959999024,
"count": 10,
"self": 1.5769060959999024
}
}
},
"_update_policy": {
"total": 311.0935637889968,
"count": 97,
"self": 245.99668919599105,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.09687459300574,
"count": 2910,
"self": 65.09687459300574
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2780001270584762e-06,
"count": 1,
"self": 1.2780001270584762e-06
},
"TrainerController._save_models": {
"total": 0.18465847300012683,
"count": 1,
"self": 0.0029018250002081913,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18175664799991864,
"count": 1,
"self": 0.18175664799991864
}
}
}
}
}
}
}