{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0229613780975342, "min": 1.0229613780975342, "max": 1.4882289171218872, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 30639.740234375, "min": 30639.740234375, "max": 45146.9140625, "count": 3 }, "Pyramids.Step.mean": { "value": 89922.0, "min": 29952.0, "max": 89922.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89922.0, "min": 29952.0, "max": 89922.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09439827501773834, "min": -0.09439827501773834, "max": -0.012767951935529709, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -22.749984741210938, "min": -22.749984741210938, "max": -3.0260045528411865, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.20313036441802979, "min": 0.20313036441802979, "max": 0.34145307540893555, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 48.95441818237305, "min": 48.95441818237305, "max": 80.92437744140625, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07180172525127432, "min": 0.06775372254005396, "max": 0.07217720247308011, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6462155272614688, "min": 0.47427605778037774, "max": 0.6462155272614688, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0011397290572731642, "min": 0.0006927422234180153, "max": 0.006533059602083988, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.010257561515458478, "min": 0.004849195563926107, "max": 0.04573141721458791, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.549340816888887e-05, "min": 7.549340816888887e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0006794406735199999, "min": 0.0006794406735199999, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12516444444444444, "min": 0.12516444444444444, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.12648, "min": 1.0911359999999999, "max": 1.2868480000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.002523928, "min": 0.002523928, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.022715352, "min": 0.022715352, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.11212483793497086, "min": 0.11212483793497086, "max": 0.45865699648857117, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.0091235637664795, "min": 1.0091235637664795, "max": 3.210598945617676, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 993.0625, "min": 993.0625, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31778.0, "min": 15984.0, "max": 31968.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9315313019324094, "min": -1.0000000521540642, "max": -0.9315313019324094, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -29.8090016618371, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9315313019324094, "min": -1.0000000521540642, "max": -0.9315313019324094, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -29.8090016618371, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.3172022206708789, "min": 1.3172022206708789, "max": 9.006343544460833, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 42.150471061468124, "min": 42.150471061468124, "max": 144.10149671137333, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682255296", "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=PyramidsTrainingRND --no-graphics --force", "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": "1682255497" }, "total": 201.13026439700002, "count": 1, "self": 0.47400341999991724, "children": { "run_training.setup": { "total": 0.11000375300000087, "count": 1, "self": 0.11000375300000087 }, "TrainerController.start_learning": { "total": 200.5462572240001, "count": 1, "self": 0.13975283000468153, "children": { "TrainerController._reset_env": { "total": 4.0618279699999675, "count": 1, "self": 4.0618279699999675 }, "TrainerController.advance": { "total": 196.22450164699558, "count": 6267, "self": 0.15010125499679816, "children": { "env_step": { "total": 138.04552506699724, "count": 6267, "self": 126.0181449070094, "children": { "SubprocessEnvManager._take_step": { "total": 11.935498925005277, "count": 6267, "self": 0.5242217450118005, "children": { "TorchPolicy.evaluate": { "total": 11.411277179993476, "count": 6265, "self": 11.411277179993476 } } }, "workers": { "total": 0.09188123498256573, "count": 6267, "self": 0.0, "children": { "worker_root": { "total": 200.05761350400144, "count": 6267, "is_parallel": true, "self": 86.16756258599503, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018129279999357095, "count": 1, "is_parallel": true, "self": 0.0005910349996156583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012218930003200512, "count": 8, "is_parallel": true, "self": 0.0012218930003200512 } } }, "UnityEnvironment.step": { "total": 0.08381813799996962, "count": 1, "is_parallel": true, "self": 0.0005884569998215738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005210179999721731, "count": 1, "is_parallel": true, "self": 0.0005210179999721731 }, "communicator.exchange": { "total": 0.08082164200004627, "count": 1, "is_parallel": true, "self": 0.08082164200004627 }, "steps_from_proto": { "total": 0.0018870210001296073, "count": 1, "is_parallel": true, "self": 0.00045310300038181595, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014339179997477913, "count": 8, "is_parallel": true, "self": 0.0014339179997477913 } } } } } } }, "UnityEnvironment.step": { "total": 113.89005091800641, "count": 6266, "is_parallel": true, "self": 3.3515432050264735, "children": { "UnityEnvironment._generate_step_input": { "total": 2.52273048599136, "count": 6266, "is_parallel": true, "self": 2.52273048599136 }, "communicator.exchange": { "total": 97.72407457399459, "count": 6266, "is_parallel": true, "self": 97.72407457399459 }, "steps_from_proto": { "total": 10.29170265299399, "count": 6266, "is_parallel": true, "self": 2.228655433984386, "children": { "_process_rank_one_or_two_observation": { "total": 8.063047219009604, "count": 50128, "is_parallel": true, "self": 8.063047219009604 } } } } } } } } } } }, "trainer_advance": { "total": 58.028875325001536, "count": 6267, "self": 0.16840663901984954, "children": { "process_trajectory": { "total": 10.285660992981775, "count": 6267, "self": 10.285660992981775 }, "_update_policy": { "total": 47.57480769299991, "count": 27, "self": 30.01514391399337, "children": { "TorchPPOOptimizer.update": { "total": 17.55966377900654, "count": 2292, "self": 17.55966377900654 } } } } } } }, "trainer_threads": { "total": 1.0639998890837887e-06, "count": 1, "self": 1.0639998890837887e-06 }, "TrainerController._save_models": { "total": 0.12017371299998558, "count": 1, "self": 0.0014467399998920882, "children": { "RLTrainer._checkpoint": { "total": 0.1187269730000935, "count": 1, "self": 0.1187269730000935 } } } } } } }