ppo-Pyramids / run_logs /timers.json
jerryvc's picture
Initial commit
eafeee9 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.206770122051239,
"min": 0.2056090086698532,
"max": 1.3927414417266846,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 6216.3369140625,
"min": 6141.9521484375,
"max": 42250.203125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999921.0,
"min": 29952.0,
"max": 2999921.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999921.0,
"min": 29952.0,
"max": 2999921.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.785740315914154,
"min": -0.10324804484844208,
"max": 0.8144811987876892,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 236.50782775878906,
"min": -24.88277816772461,
"max": 243.52987670898438,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0031998937483876944,
"min": -0.007742323912680149,
"max": 0.43855854868888855,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.9631680250167847,
"min": -2.260758638381958,
"max": 103.9383773803711,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06644852563699041,
"min": 0.06317429213344844,
"max": 0.07464155548759607,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9302793589178657,
"min": 0.5195865159169851,
"max": 1.110843459438697,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013420625872021743,
"min": 6.48850558372636e-05,
"max": 0.01638003544658892,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18788876220830442,
"min": 0.0008435057258844269,
"max": 0.2355465262200382,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.546292341745237e-06,
"min": 1.546292341745237e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1648092784433318e-05,
"min": 2.1648092784433318e-05,
"max": 0.003843440118853333,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10051539761904763,
"min": 0.10051539761904763,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4072155666666668,
"min": 1.3962282666666668,
"max": 2.737539133333334,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.14882221428571e-05,
"min": 6.14882221428571e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008608351099999996,
"min": 0.0008608351099999996,
"max": 0.128126552,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0059103225357830524,
"min": 0.005707846488803625,
"max": 0.4884497821331024,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08274451643228531,
"min": 0.07990985363721848,
"max": 3.4191484451293945,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 236.61111111111111,
"min": 221.91603053435114,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29813.0,
"min": 15984.0,
"max": 32861.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7473247915506362,
"min": -1.0000000521540642,
"max": 1.7628152608188965,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 218.41559894382954,
"min": -30.994001626968384,
"max": 233.57079738378525,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7473247915506362,
"min": -1.0000000521540642,
"max": 1.7628152608188965,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 218.41559894382954,
"min": -30.994001626968384,
"max": 233.57079738378525,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.014788529093842954,
"min": 0.01375041816477628,
"max": 10.11939924582839,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.8485661367303692,
"min": 1.7296363297500648,
"max": 161.91038793325424,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1728698345",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728703644"
},
"total": 5299.500081418999,
"count": 1,
"self": 0.2200236940116156,
"children": {
"run_training.setup": {
"total": 0.04211423499509692,
"count": 1,
"self": 0.04211423499509692
},
"TrainerController.start_learning": {
"total": 5299.237943489992,
"count": 1,
"self": 2.8504408855369547,
"children": {
"TrainerController._reset_env": {
"total": 1.2168609960062895,
"count": 1,
"self": 1.2168609960062895
},
"TrainerController.advance": {
"total": 5295.095314422448,
"count": 194082,
"self": 2.596151805802947,
"children": {
"env_step": {
"total": 3493.9227866347064,
"count": 194082,
"self": 2973.8017833740596,
"children": {
"SubprocessEnvManager._take_step": {
"total": 518.3494219050917,
"count": 194082,
"self": 7.489498783717863,
"children": {
"TorchPolicy.evaluate": {
"total": 510.85992312137387,
"count": 187557,
"self": 510.85992312137387
}
}
},
"workers": {
"total": 1.7715813555550994,
"count": 194082,
"self": 0.0,
"children": {
"worker_root": {
"total": 5292.2500225746335,
"count": 194082,
"is_parallel": true,
"self": 2515.391578185139,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014511610061163083,
"count": 1,
"is_parallel": true,
"self": 0.0004939070204272866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009572539856890216,
"count": 8,
"is_parallel": true,
"self": 0.0009572539856890216
}
}
},
"UnityEnvironment.step": {
"total": 0.030801828994299285,
"count": 1,
"is_parallel": true,
"self": 0.00026234498363919556,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022578300558961928,
"count": 1,
"is_parallel": true,
"self": 0.00022578300558961928
},
"communicator.exchange": {
"total": 0.0295974899927387,
"count": 1,
"is_parallel": true,
"self": 0.0295974899927387
},
"steps_from_proto": {
"total": 0.0007162110123317689,
"count": 1,
"is_parallel": true,
"self": 0.0001918530324473977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005243579798843712,
"count": 8,
"is_parallel": true,
"self": 0.0005243579798843712
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2776.8584443894943,
"count": 194081,
"is_parallel": true,
"self": 37.80760770587949,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.004874145204667,
"count": 194081,
"is_parallel": true,
"self": 28.004874145204667
},
"communicator.exchange": {
"total": 2601.1372125845955,
"count": 194081,
"is_parallel": true,
"self": 2601.1372125845955
},
"steps_from_proto": {
"total": 109.90874995381455,
"count": 194081,
"is_parallel": true,
"self": 27.71920206642244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.18954788739211,
"count": 1552648,
"is_parallel": true,
"self": 82.18954788739211
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1798.5763759819383,
"count": 194082,
"self": 5.4938474735827185,
"children": {
"process_trajectory": {
"total": 323.3683632181928,
"count": 194082,
"self": 322.9126156322309,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4557475859619444,
"count": 6,
"self": 0.4557475859619444
}
}
},
"_update_policy": {
"total": 1469.7141652901628,
"count": 1396,
"self": 696.4837890552735,
"children": {
"TorchPPOOptimizer.update": {
"total": 773.2303762348893,
"count": 68313,
"self": 773.2303762348893
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.199996616691351e-07,
"count": 1,
"self": 7.199996616691351e-07
},
"TrainerController._save_models": {
"total": 0.07532646600157022,
"count": 1,
"self": 0.001134089005063288,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07419237699650694,
"count": 1,
"self": 0.07419237699650694
}
}
}
}
}
}
}