ppo-Pyramids / run_logs /timers.json
jake-snake's picture
First Push
32b6bef verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.8114615082740784,
"min": 0.8103852272033691,
"max": 1.4139457941055298,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 24369.8125,
"min": 24233.759765625,
"max": 42893.4609375,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479980.0,
"min": 29952.0,
"max": 479980.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479980.0,
"min": 29952.0,
"max": 479980.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.056411806493997574,
"min": -0.10649660229682922,
"max": -0.037700530141592026,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -13.651657104492188,
"min": -25.665681838989258,
"max": -9.123528480529785,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03295939788222313,
"min": 0.0313684344291687,
"max": 0.33592432737350464,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.976174354553223,
"min": 7.62252950668335,
"max": 80.724853515625,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06950854517789154,
"min": 0.06596464200430556,
"max": 0.07247081982804691,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9731196324904815,
"min": 0.4933850102226287,
"max": 0.9971331174019725,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.002613952423049921,
"min": 7.499167543417361e-05,
"max": 0.009551110080720886,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.0365953339226989,
"min": 0.0010498834560784306,
"max": 0.0668577705650462,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.0001602162465946,
"min": 0.0001602162465946,
"max": 0.00029515063018788575,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0022430274523244,
"min": 0.0020660544113152,
"max": 0.0035081945306018997,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.15340540000000003,
"min": 0.15340540000000003,
"max": 0.19838354285714285,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.1476756000000004,
"min": 1.3886848,
"max": 2.5693981000000004,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.005345199459999999,
"min": 0.005345199459999999,
"max": 0.00983851593142857,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.07483279243999999,
"min": 0.06886961152,
"max": 0.11696287018999998,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0283135287463665,
"min": 0.0283135287463665,
"max": 0.5130571126937866,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3963893949985504,
"min": 0.3963893949985504,
"max": 3.591399669647217,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 940.5625,
"min": 917.4411764705883,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30098.0,
"min": 15984.0,
"max": 32310.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.5660750498063862,
"min": -1.0000000521540642,
"max": -0.37001822979161236,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -18.11440159380436,
"min": -30.9894015789032,
"max": -12.210601583123207,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.5660750498063862,
"min": -1.0000000521540642,
"max": -0.37001822979161236,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -18.11440159380436,
"min": -30.9894015789032,
"max": -12.210601583123207,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.27796140196733177,
"min": 0.27796140196733177,
"max": 10.674773597158492,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.894764862954617,
"min": 8.894764862954617,
"max": 170.79637755453587,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1760569254",
"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/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": "2.9.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760570433"
},
"total": 1179.701913368,
"count": 1,
"self": 0.8909838590000163,
"children": {
"run_training.setup": {
"total": 0.026569723999955386,
"count": 1,
"self": 0.026569723999955386
},
"TrainerController.start_learning": {
"total": 1178.784359785,
"count": 1,
"self": 0.7267529719981667,
"children": {
"TrainerController._reset_env": {
"total": 1.9782569789999798,
"count": 1,
"self": 1.9782569789999798
},
"TrainerController.advance": {
"total": 1175.9851165600019,
"count": 31560,
"self": 0.7710480649900546,
"children": {
"env_step": {
"total": 821.724655386004,
"count": 31560,
"self": 740.4526292159662,
"children": {
"SubprocessEnvManager._take_step": {
"total": 80.84157832900974,
"count": 31560,
"self": 2.5624614030059547,
"children": {
"TorchPolicy.evaluate": {
"total": 78.27911692600378,
"count": 31304,
"self": 78.27911692600378
}
}
},
"workers": {
"total": 0.4304478410280126,
"count": 31560,
"self": 0.0,
"children": {
"worker_root": {
"total": 1175.6388520709895,
"count": 31560,
"is_parallel": true,
"self": 498.6948732600097,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002110029999926155,
"count": 1,
"is_parallel": true,
"self": 0.0007237829997848166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013862470001413385,
"count": 8,
"is_parallel": true,
"self": 0.0013862470001413385
}
}
},
"UnityEnvironment.step": {
"total": 0.05960426199999347,
"count": 1,
"is_parallel": true,
"self": 0.0005982049999602168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005655709999246028,
"count": 1,
"is_parallel": true,
"self": 0.0005655709999246028
},
"communicator.exchange": {
"total": 0.056679738000070756,
"count": 1,
"is_parallel": true,
"self": 0.056679738000070756
},
"steps_from_proto": {
"total": 0.0017607480000378928,
"count": 1,
"is_parallel": true,
"self": 0.0003902930000094784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013704550000284144,
"count": 8,
"is_parallel": true,
"self": 0.0013704550000284144
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 676.9439788109798,
"count": 31559,
"is_parallel": true,
"self": 18.59048901894562,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.290932165011895,
"count": 31559,
"is_parallel": true,
"self": 13.290932165011895
},
"communicator.exchange": {
"total": 582.2281431640058,
"count": 31559,
"is_parallel": true,
"self": 582.2281431640058
},
"steps_from_proto": {
"total": 62.834414463016515,
"count": 31559,
"is_parallel": true,
"self": 12.825841859996672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 50.00857260301984,
"count": 252472,
"is_parallel": true,
"self": 50.00857260301984
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 353.48941310900796,
"count": 31560,
"self": 1.1953593199822308,
"children": {
"process_trajectory": {
"total": 67.34398841802602,
"count": 31560,
"self": 67.2574833890261,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08650502899990897,
"count": 1,
"self": 0.08650502899990897
}
}
},
"_update_policy": {
"total": 284.9500653709997,
"count": 212,
"self": 161.27328650500192,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.67677886599779,
"count": 11439,
"self": 123.67677886599779
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0942332740000893,
"count": 1,
"self": 4.373799993118155e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09418953600015811,
"count": 1,
"self": 0.09418953600015811
}
}
}
}
}
}
}