{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4383748471736908, "min": 0.4383748471736908, "max": 1.5374524593353271, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13193.3291015625, "min": 13193.3291015625, "max": 46640.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5079846978187561, "min": -0.22263436019420624, "max": 0.5079846978187561, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.2037811279297, "min": -52.76434326171875, "max": 140.2037811279297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015380463562905788, "min": -0.0013826994691044092, "max": 0.4471650719642639, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.2450079917907715, "min": -0.33737868070602417, "max": 105.97811889648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06767598536163051, "min": 0.06614082330828643, "max": 0.0750729314328585, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0151397804244577, "min": 0.5082534573853134, "max": 1.0510210400600188, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01583725335205802, "min": 0.000370919254713319, "max": 0.01583725335205802, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23755880028087029, "min": 0.004821950311273147, "max": 0.23755880028087029, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.510277496606667e-06, "min": 7.510277496606667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001126541624491, "min": 0.0001126541624491, "max": 0.0032528627157125, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250339333333332, "min": 0.10250339333333332, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375508999999998, "min": 1.3886848, "max": 2.4019303, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026008899400000005, "min": 0.00026008899400000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039013349100000005, "min": 0.0039013349100000005, "max": 0.10845032125, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008669668808579445, "min": 0.008669668808579445, "max": 0.2906513214111328, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13004502654075623, "min": 0.12576048076152802, "max": 2.0345592498779297, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 365.94117647058823, "min": 365.94117647058823, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31105.0, "min": 15984.0, "max": 32724.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5199325370580652, "min": -1.0000000521540642, "max": 1.5303839832544326, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.7141981869936, "min": -30.999201610684395, "max": 130.7141981869936, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5199325370580652, "min": -1.0000000521540642, "max": 1.5303839832544326, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.7141981869936, "min": -30.999201610684395, "max": 130.7141981869936, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03288487576457217, "min": 0.03288487576457217, "max": 5.715780191123486, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8280993157532066, "min": 2.705640456362744, "max": 91.45248305797577, "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": "1743006412", "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=Pyramids1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743008095" }, "total": 1682.4043333689997, "count": 1, "self": 0.3308606430000509, "children": { "run_training.setup": { "total": 0.022087654999722872, "count": 1, "self": 0.022087654999722872 }, "TrainerController.start_learning": { "total": 1682.051385071, "count": 1, "self": 1.0957553690504938, "children": { "TrainerController._reset_env": { "total": 2.2655211070000405, "count": 1, "self": 2.2655211070000405 }, "TrainerController.advance": { "total": 1678.6008556439483, "count": 63587, "self": 1.1251304790248469, "children": { "env_step": { "total": 1094.0155611188661, "count": 63587, "self": 960.9409637176518, "children": { "SubprocessEnvManager._take_step": { "total": 132.39931852602876, "count": 63587, "self": 4.0109017480922375, "children": { "TorchPolicy.evaluate": { "total": 128.38841677793653, "count": 62549, "self": 128.38841677793653 } } }, "workers": { "total": 0.6752788751855405, "count": 63587, "self": 0.0, "children": { "worker_root": { "total": 1679.970926014007, "count": 63587, "is_parallel": true, "self": 805.1095039979891, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002073827000003803, "count": 1, "is_parallel": true, "self": 0.0006601839991162706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014136430008875323, "count": 8, "is_parallel": true, "self": 0.0014136430008875323 } } }, "UnityEnvironment.step": { "total": 0.034926434000226436, "count": 1, "is_parallel": true, "self": 0.0003410270005588245, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026866500002142857, "count": 1, "is_parallel": true, "self": 0.00026866500002142857 }, "communicator.exchange": { "total": 0.033327857999665866, "count": 1, "is_parallel": true, "self": 0.033327857999665866 }, "steps_from_proto": { "total": 0.0009888839999803167, "count": 1, "is_parallel": true, "self": 0.00025690799975564005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007319760002246767, "count": 8, "is_parallel": true, "self": 0.0007319760002246767 } } } } } } }, "UnityEnvironment.step": { "total": 874.861422016018, "count": 63586, "is_parallel": true, "self": 22.39549254911799, "children": { "UnityEnvironment._generate_step_input": { "total": 15.804825727955176, "count": 63586, "is_parallel": true, "self": 15.804825727955176 }, "communicator.exchange": { "total": 767.4515109929325, "count": 63586, "is_parallel": true, "self": 767.4515109929325 }, "steps_from_proto": { "total": 69.20959274601228, "count": 63586, "is_parallel": true, "self": 14.190171379028016, "children": { "_process_rank_one_or_two_observation": { "total": 55.01942136698426, "count": 508688, "is_parallel": true, "self": 55.01942136698426 } } } } } } } } } } }, "trainer_advance": { "total": 583.4601640460573, "count": 63587, "self": 2.069307583149566, "children": { "process_trajectory": { "total": 109.05045299190988, "count": 63587, "self": 108.84455155191017, "children": { "RLTrainer._checkpoint": { "total": 0.20590143999970678, "count": 2, "self": 0.20590143999970678 } } }, "_update_policy": { "total": 472.3404034709979, "count": 443, "self": 255.27660092694668, "children": { "TorchPPOOptimizer.update": { "total": 217.0638025440512, "count": 22824, "self": 217.0638025440512 } } } } } } }, "trainer_threads": { "total": 8.80000698089134e-07, "count": 1, "self": 8.80000698089134e-07 }, "TrainerController._save_models": { "total": 0.08925207100037369, "count": 1, "self": 0.0014386470002136775, "children": { "RLTrainer._checkpoint": { "total": 0.08781342400016001, "count": 1, "self": 0.08781342400016001 } } } } } } }