{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.24506981670856476, "min": 0.241383358836174, "max": 1.4179835319519043, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7359.9365234375, "min": 7218.328125, "max": 43015.94921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989964.0, "min": 29988.0, "max": 989964.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989964.0, "min": 29988.0, "max": 989964.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5139384865760803, "min": -0.08903287351131439, "max": 0.6125004887580872, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.79127502441406, "min": -21.367889404296875, "max": 169.76962280273438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023036247119307518, "min": 0.016653509810566902, "max": 0.3332921862602234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.265859127044678, "min": 4.596368789672852, "max": 79.32353973388672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0669921828181638, "min": 0.06526319732335499, "max": 0.07474776324669333, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9378905594542932, "min": 0.5232343427268533, "max": 1.0838191963654633, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016409799418137742, "min": 6.211209941257566e-05, "max": 0.016409799418137742, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2297371918539284, "min": 0.0005590088947131809, "max": 0.23743053100285277, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.278290431078573e-06, "min": 7.278290431078573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010189606603510002, "min": 0.00010189606603510002, "max": 0.0036341953886016, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242606428571431, "min": 0.10242606428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339649000000003, "min": 1.3886848, "max": 2.6113984, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025236382214285723, "min": 0.00025236382214285723, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003533093510000001, "min": 0.003533093510000001, "max": 0.12115870016000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011055772192776203, "min": 0.011019249446690083, "max": 0.5061588883399963, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1547808051109314, "min": 0.1547808051109314, "max": 3.54311203956604, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.9529411764706, "min": 308.67021276595744, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29321.0, "min": 16787.0, "max": 33323.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5623767216538273, "min": -0.9999742455059483, "max": 1.64985955601677, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.36439806222916, "min": -31.998401656746864, "max": 157.68279846012592, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5623767216538273, "min": -0.9999742455059483, "max": 1.64985955601677, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.36439806222916, "min": -31.998401656746864, "max": 157.68279846012592, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039896355555758295, "min": 0.03745720751805336, "max": 9.62196639486972, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.431086577795213, "min": 3.431086577795213, "max": 163.57342871278524, "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": "1683488478", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683490816" }, "total": 2338.780038045, "count": 1, "self": 0.4740612259993213, "children": { "run_training.setup": { "total": 0.04080725599942525, "count": 1, "self": 0.04080725599942525 }, "TrainerController.start_learning": { "total": 2338.265169563001, "count": 1, "self": 1.5309565789730186, "children": { "TrainerController._reset_env": { "total": 5.113940167999317, "count": 1, "self": 5.113940167999317 }, "TrainerController.advance": { "total": 2331.487815901027, "count": 64047, "self": 1.473818019941973, "children": { "env_step": { "total": 1669.3526847670455, "count": 64047, "self": 1551.208181942131, "children": { "SubprocessEnvManager._take_step": { "total": 117.26552390898087, "count": 64047, "self": 4.79033876468111, "children": { "TorchPolicy.evaluate": { "total": 112.47518514429976, "count": 62566, "self": 112.47518514429976 } } }, "workers": { "total": 0.8789789159336578, "count": 64047, "self": 0.0, "children": { "worker_root": { "total": 2332.3673347649055, "count": 64047, "is_parallel": true, "self": 899.3011065539768, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002138265999747091, "count": 1, "is_parallel": true, "self": 0.000491739001517999, "children": { "_process_rank_one_or_two_observation": { "total": 0.001646526998229092, "count": 8, "is_parallel": true, "self": 0.001646526998229092 } } }, "UnityEnvironment.step": { "total": 0.04512970699943253, "count": 1, "is_parallel": true, "self": 0.000506116999531514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004488020003918791, "count": 1, "is_parallel": true, "self": 0.0004488020003918791 }, "communicator.exchange": { "total": 0.04255613799978164, "count": 1, "is_parallel": true, "self": 0.04255613799978164 }, "steps_from_proto": { "total": 0.001618649999727495, "count": 1, "is_parallel": true, "self": 0.0003552329999365611, "children": { "_process_rank_one_or_two_observation": { "total": 0.001263416999790934, "count": 8, "is_parallel": true, "self": 0.001263416999790934 } } } } } } }, "UnityEnvironment.step": { "total": 1433.0662282109288, "count": 64046, "is_parallel": true, "self": 32.150363692963765, "children": { "UnityEnvironment._generate_step_input": { "total": 22.664865339063, "count": 64046, "is_parallel": true, "self": 22.664865339063 }, "communicator.exchange": { "total": 1278.7326714070705, "count": 64046, "is_parallel": true, "self": 1278.7326714070705 }, "steps_from_proto": { "total": 99.51832777183154, "count": 64046, "is_parallel": true, "self": 20.479833020986916, "children": { "_process_rank_one_or_two_observation": { "total": 79.03849475084462, "count": 512368, "is_parallel": true, "self": 79.03849475084462 } } } } } } } } } } }, "trainer_advance": { "total": 660.6613131140393, "count": 64047, "self": 2.767265515875806, "children": { "process_trajectory": { "total": 108.5859701151785, "count": 64047, "self": 108.25465404917759, "children": { "RLTrainer._checkpoint": { "total": 0.3313160660009089, "count": 2, "self": 0.3313160660009089 } } }, "_update_policy": { "total": 549.308077482985, "count": 452, "self": 346.81208176593464, "children": { "TorchPPOOptimizer.update": { "total": 202.4959957170504, "count": 22770, "self": 202.4959957170504 } } } } } } }, "trainer_threads": { "total": 9.760005923453718e-07, "count": 1, "self": 9.760005923453718e-07 }, "TrainerController._save_models": { "total": 0.13245593900137465, "count": 1, "self": 0.0024143980008375365, "children": { "RLTrainer._checkpoint": { "total": 0.1300415410005371, "count": 1, "self": 0.1300415410005371 } } } } } } }