Pyramids / run_logs /timers.json
MysteryManav's picture
PyramidsRND Env
6ef6f41 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.11201507598161697,
"min": 0.11201507598161697,
"max": 1.3795297145843506,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 3329.984130859375,
"min": 3329.984130859375,
"max": 41849.4140625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999970.0,
"min": 29914.0,
"max": 2999970.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999970.0,
"min": 29914.0,
"max": 2999970.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7661625146865845,
"min": -0.09787502884864807,
"max": 0.8816738724708557,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 226.0179443359375,
"min": -23.587881088256836,
"max": 277.6173400878906,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00927724875509739,
"min": -0.04299420490860939,
"max": 0.4846227467060089,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.736788272857666,
"min": -12.55430793762207,
"max": 114.8555908203125,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06929154200366887,
"min": 0.06362488486255252,
"max": 0.07447225737823396,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9700815880513641,
"min": 0.4793419268065207,
"max": 1.0550356280291453,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013973313895806133,
"min": 0.0006138173560240632,
"max": 0.01696922489627315,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19562639454128586,
"min": 0.008593442984336884,
"max": 0.23792842536446793,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4114638152595238e-06,
"min": 1.4114638152595238e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 1.9760493413633333e-05,
"min": 1.9760493413633333e-05,
"max": 0.004011005662998134,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10047045476190476,
"min": 0.10047045476190476,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4065863666666667,
"min": 1.3962282666666668,
"max": 2.8123959,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.69984307142857e-05,
"min": 5.69984307142857e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0007979780299999998,
"min": 0.0007979780299999998,
"max": 0.13370648648,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007118559442460537,
"min": 0.007118559442460537,
"max": 0.5806519389152527,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09965983033180237,
"min": 0.09965983033180237,
"max": 4.064563751220703,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 243.91379310344828,
"min": 202.17142857142858,
"max": 990.6470588235294,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28294.0,
"min": 16841.0,
"max": 32795.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7388396395434593,
"min": -0.9235333836439884,
"max": 1.7978285585130964,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 201.70539818704128,
"min": -30.476601660251617,
"max": 267.56199768185616,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7388396395434593,
"min": -0.9235333836439884,
"max": 1.7978285585130964,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 201.70539818704128,
"min": -30.476601660251617,
"max": 267.56199768185616,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01854382207740604,
"min": 0.015736044501606778,
"max": 11.382168634849435,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.1510833609791007,
"min": 2.1510833609791007,
"max": 193.49686679244041,
"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": "1748874431",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/manav/Code/AIML/DRL/.conda/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --width=1280 --height=740 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748878314"
},
"total": 3882.6733018600025,
"count": 1,
"self": 0.5451355530021829,
"children": {
"run_training.setup": {
"total": 0.029582277998997597,
"count": 1,
"self": 0.029582277998997597
},
"TrainerController.start_learning": {
"total": 3882.0985840290014,
"count": 1,
"self": 3.9185802737301856,
"children": {
"TrainerController._reset_env": {
"total": 2.821271362998232,
"count": 1,
"self": 2.821271362998232
},
"TrainerController.advance": {
"total": 3875.2902588942707,
"count": 195366,
"self": 3.747796025523712,
"children": {
"env_step": {
"total": 2587.801255873357,
"count": 195366,
"self": 2221.116065284328,
"children": {
"SubprocessEnvManager._take_step": {
"total": 364.1116507843508,
"count": 195366,
"self": 11.062465863011312,
"children": {
"TorchPolicy.evaluate": {
"total": 353.0491849213395,
"count": 187543,
"self": 353.0491849213395
}
}
},
"workers": {
"total": 2.5735398046781484,
"count": 195366,
"self": 0.0,
"children": {
"worker_root": {
"total": 3877.003493752265,
"count": 195366,
"is_parallel": true,
"self": 1903.140750078208,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001701354001852451,
"count": 1,
"is_parallel": true,
"self": 0.00042423600098118186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001277118000871269,
"count": 8,
"is_parallel": true,
"self": 0.001277118000871269
}
}
},
"UnityEnvironment.step": {
"total": 0.03242192700054147,
"count": 1,
"is_parallel": true,
"self": 0.0003057159992749803,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002500990012777038,
"count": 1,
"is_parallel": true,
"self": 0.0002500990012777038
},
"communicator.exchange": {
"total": 0.03107390100194607,
"count": 1,
"is_parallel": true,
"self": 0.03107390100194607
},
"steps_from_proto": {
"total": 0.0007922109980427194,
"count": 1,
"is_parallel": true,
"self": 0.00019557899940991774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005966319986328017,
"count": 8,
"is_parallel": true,
"self": 0.0005966319986328017
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1973.8627436740571,
"count": 195365,
"is_parallel": true,
"self": 49.2054625875644,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 33.093910662206326,
"count": 195365,
"is_parallel": true,
"self": 33.093910662206326
},
"communicator.exchange": {
"total": 1756.8646017534884,
"count": 195365,
"is_parallel": true,
"self": 1756.8646017534884
},
"steps_from_proto": {
"total": 134.69876867079802,
"count": 195365,
"is_parallel": true,
"self": 31.17848266232977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 103.52028600846825,
"count": 1562920,
"is_parallel": true,
"self": 103.52028600846825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1283.7412069953898,
"count": 195366,
"self": 6.871546429767477,
"children": {
"process_trajectory": {
"total": 267.29134076553964,
"count": 195366,
"self": 266.84834177053926,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4429989950003801,
"count": 6,
"self": 0.4429989950003801
}
}
},
"_update_policy": {
"total": 1009.5783198000827,
"count": 1403,
"self": 575.9536008172545,
"children": {
"TorchPPOOptimizer.update": {
"total": 433.6247189828282,
"count": 68364,
"self": 433.6247189828282
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.949994713068008e-07,
"count": 1,
"self": 6.949994713068008e-07
},
"TrainerController._save_models": {
"total": 0.06847280300280545,
"count": 1,
"self": 0.0026138070024899207,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06585899600031553,
"count": 1,
"self": 0.06585899600031553
}
}
}
}
}
}
}