ppo-Pyramids / run_logs /timers.json
Hariprasath28's picture
First Push
18cc284
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.404713898897171,
"min": 0.388362318277359,
"max": 1.447376012802124,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12167.318359375,
"min": 11737.8623046875,
"max": 43907.59765625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989946.0,
"min": 29952.0,
"max": 989946.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989946.0,
"min": 29952.0,
"max": 989946.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5149554014205933,
"min": -0.09209084510803223,
"max": 0.5149554014205933,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 141.0977783203125,
"min": -22.193893432617188,
"max": 141.0977783203125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.04016876593232155,
"min": -0.04016876593232155,
"max": 0.4002934992313385,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -11.006241798400879,
"min": -11.006241798400879,
"max": 94.86956024169922,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07029258864418982,
"min": 0.06701452440361451,
"max": 0.07344866531649316,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9840962410186574,
"min": 0.5017477453264124,
"max": 1.0413641529400288,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014035726248472375,
"min": 0.0005578439872526611,
"max": 0.015477183326386363,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19650016747861324,
"min": 0.007251971834284593,
"max": 0.21668056656940907,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.34004755335e-06,
"min": 7.34004755335e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001027606657469,
"min": 0.0001027606657469,
"max": 0.0033745624751458994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244665,
"min": 0.10244665,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4342531,
"min": 1.3886848,
"max": 2.4248541,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025442033500000006,
"min": 0.00025442033500000006,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003561884690000001,
"min": 0.003561884690000001,
"max": 0.11250292459000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01115137618035078,
"min": 0.01115137618035078,
"max": 0.3420438766479492,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15611927211284637,
"min": 0.15611927211284637,
"max": 2.3943071365356445,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 366.29761904761904,
"min": 366.29761904761904,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30769.0,
"min": 15984.0,
"max": 33016.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5108047313988209,
"min": -1.0000000521540642,
"max": 1.5108047313988209,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 126.90759743750095,
"min": -30.352201730012894,
"max": 126.90759743750095,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5108047313988209,
"min": -1.0000000521540642,
"max": 1.5108047313988209,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 126.90759743750095,
"min": -30.352201730012894,
"max": 126.90759743750095,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04211168914385087,
"min": 0.04211168914385087,
"max": 6.5513052036985755,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.5373818880834733,
"min": 3.5084612832870334,
"max": 104.82088325917721,
"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": "1682591934",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1682593994"
},
"total": 2060.1114051409995,
"count": 1,
"self": 0.4768918109994047,
"children": {
"run_training.setup": {
"total": 0.1095395570000619,
"count": 1,
"self": 0.1095395570000619
},
"TrainerController.start_learning": {
"total": 2059.524973773,
"count": 1,
"self": 1.3185361310061126,
"children": {
"TrainerController._reset_env": {
"total": 3.7919083669999054,
"count": 1,
"self": 3.7919083669999054
},
"TrainerController.advance": {
"total": 2054.3235150619935,
"count": 63600,
"self": 1.3575455678897015,
"children": {
"env_step": {
"total": 1430.0237639810039,
"count": 63600,
"self": 1324.904932217009,
"children": {
"SubprocessEnvManager._take_step": {
"total": 104.28504615801194,
"count": 63600,
"self": 4.656458474026294,
"children": {
"TorchPolicy.evaluate": {
"total": 99.62858768398564,
"count": 62552,
"self": 99.62858768398564
}
}
},
"workers": {
"total": 0.8337856059829392,
"count": 63600,
"self": 0.0,
"children": {
"worker_root": {
"total": 2054.867181988064,
"count": 63600,
"is_parallel": true,
"self": 836.3669420321385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001812748000247666,
"count": 1,
"is_parallel": true,
"self": 0.0005708360008611635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012419119993865024,
"count": 8,
"is_parallel": true,
"self": 0.0012419119993865024
}
}
},
"UnityEnvironment.step": {
"total": 0.046316713000123855,
"count": 1,
"is_parallel": true,
"self": 0.0005523410000023432,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004899619998468552,
"count": 1,
"is_parallel": true,
"self": 0.0004899619998468552
},
"communicator.exchange": {
"total": 0.043639080000048125,
"count": 1,
"is_parallel": true,
"self": 0.043639080000048125
},
"steps_from_proto": {
"total": 0.0016353300002265314,
"count": 1,
"is_parallel": true,
"self": 0.00038040100025682477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012549289999697066,
"count": 8,
"is_parallel": true,
"self": 0.0012549289999697066
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1218.5002399559257,
"count": 63599,
"is_parallel": true,
"self": 32.03386976389129,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.499093553989496,
"count": 63599,
"is_parallel": true,
"self": 22.499093553989496
},
"communicator.exchange": {
"total": 1072.855127122058,
"count": 63599,
"is_parallel": true,
"self": 1072.855127122058
},
"steps_from_proto": {
"total": 91.11214951598686,
"count": 63599,
"is_parallel": true,
"self": 19.206868793090052,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.9052807228968,
"count": 508792,
"is_parallel": true,
"self": 71.9052807228968
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 622.9422055130999,
"count": 63600,
"self": 2.521415385218006,
"children": {
"process_trajectory": {
"total": 103.45003195489062,
"count": 63600,
"self": 103.24269225589069,
"children": {
"RLTrainer._checkpoint": {
"total": 0.207339698999931,
"count": 2,
"self": 0.207339698999931
}
}
},
"_update_policy": {
"total": 516.9707581729913,
"count": 447,
"self": 332.0455394859555,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.9252186870358,
"count": 22770,
"self": 184.9252186870358
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.540000635548495e-07,
"count": 1,
"self": 8.540000635548495e-07
},
"TrainerController._save_models": {
"total": 0.0910133590004989,
"count": 1,
"self": 0.0015288690010493156,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08948448999944958,
"count": 1,
"self": 0.08948448999944958
}
}
}
}
}
}
}