{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13290271162986755, "min": 0.12789878249168396, "max": 1.4858391284942627, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4042.368896484375, "min": 3853.33447265625, "max": 45074.4140625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999992.0, "min": 29952.0, "max": 2999992.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999992.0, "min": 29952.0, "max": 2999992.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8781569600105286, "min": -0.12236586213111877, "max": 0.9151589870452881, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 273.1068115234375, "min": -29.000709533691406, "max": 284.38653564453125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006632458418607712, "min": -0.020884422585368156, "max": 0.39716818928718567, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.062694549560547, "min": -5.288554668426514, "max": 96.11470031738281, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06506411665551631, "min": 0.06408956220686722, "max": 0.07525796355496693, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9108976331772284, "min": 0.5052430418252427, "max": 1.0577264537820228, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01427382609870706, "min": 0.0006446951939510183, "max": 0.01678641162288841, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19983356538189884, "min": 0.009025732715314256, "max": 0.2360688330469808, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4582637996595273e-06, "min": 1.4582637996595273e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0415693195233382e-05, "min": 2.0415693195233382e-05, "max": 0.004053285548904833, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048605476190477, "min": 0.10048605476190477, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068047666666668, "min": 1.3962282666666668, "max": 2.782674366666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.855687071428584e-05, "min": 5.855687071428584e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008197961900000018, "min": 0.0008197961900000018, "max": 0.13511440715, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007308993022888899, "min": 0.007308993022888899, "max": 0.5484139919281006, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10232590138912201, "min": 0.10232590138912201, "max": 3.838897943496704, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 189.94078947368422, "min": 189.94078947368422, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28871.0, "min": 15984.0, "max": 33328.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.8100591951883154, "min": -1.0000000521540642, "max": 1.8100591951883154, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 275.1289976686239, "min": -28.733201660215855, "max": 283.29299825429916, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.8100591951883154, "min": -1.0000000521540642, "max": 1.8100591951883154, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 275.1289976686239, "min": -28.733201660215855, "max": 283.29299825429916, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014533310405520177, "min": 0.014533310405520177, "max": 11.228965627029538, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.209063181639067, "min": 2.0961884391417698, "max": 179.6634500324726, "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": "1750763406", "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=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750771052" }, "total": 7645.694792222, "count": 1, "self": 0.9794089309989431, "children": { "run_training.setup": { "total": 0.02157044799992036, "count": 1, "self": 0.02157044799992036 }, "TrainerController.start_learning": { "total": 7644.693812843001, "count": 1, "self": 4.588773509979546, "children": { "TrainerController._reset_env": { "total": 2.1828167599999233, "count": 1, "self": 2.1828167599999233 }, "TrainerController.advance": { "total": 7637.8018559010225, "count": 195600, "self": 4.719293915488379, "children": { "env_step": { "total": 5626.894429259842, "count": 195600, "self": 5146.727874846747, "children": { "SubprocessEnvManager._take_step": { "total": 477.40665676001095, "count": 195600, "self": 14.216659620947212, "children": { "TorchPolicy.evaluate": { "total": 463.18999713906373, "count": 187574, "self": 463.18999713906373 } } }, "workers": { "total": 2.7598976530837263, "count": 195600, "self": 0.0, "children": { "worker_root": { "total": 7625.430164406907, "count": 195600, "is_parallel": true, "self": 2848.396998589962, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001823471000079735, "count": 1, "is_parallel": true, "self": 0.0006077519999507786, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012157190001289564, "count": 8, "is_parallel": true, "self": 0.0012157190001289564 } } }, "UnityEnvironment.step": { "total": 0.05122724600005313, "count": 1, "is_parallel": true, "self": 0.0005564780003624037, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004937919998155849, "count": 1, "is_parallel": true, "self": 0.0004937919998155849 }, "communicator.exchange": { "total": 0.0484254890000102, "count": 1, "is_parallel": true, "self": 0.0484254890000102 }, "steps_from_proto": { "total": 0.0017514869998649374, "count": 1, "is_parallel": true, "self": 0.0003676389994780038, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013838480003869336, "count": 8, "is_parallel": true, "self": 0.0013838480003869336 } } } } } } }, "UnityEnvironment.step": { "total": 4777.033165816945, "count": 195599, "is_parallel": true, "self": 98.63368456020089, "children": { "UnityEnvironment._generate_step_input": { "total": 71.06313119808624, "count": 195599, "is_parallel": true, "self": 71.06313119808624 }, "communicator.exchange": { "total": 4303.018403509659, "count": 195599, "is_parallel": true, "self": 4303.018403509659 }, "steps_from_proto": { "total": 304.3179465489991, "count": 195599, "is_parallel": true, "self": 63.13909981814459, "children": { "_process_rank_one_or_two_observation": { "total": 241.1788467308545, "count": 1564792, "is_parallel": true, "self": 241.1788467308545 } } } } } } } } } } }, "trainer_advance": { "total": 2006.1881327256926, "count": 195600, "self": 9.261552938832665, "children": { "process_trajectory": { "total": 401.0850423738832, "count": 195600, "self": 400.4784441798836, "children": { "RLTrainer._checkpoint": { "total": 0.6065981939996163, "count": 6, "self": 0.6065981939996163 } } }, "_update_policy": { "total": 1595.8415374129768, "count": 1407, "self": 884.4250603538953, "children": { "TorchPPOOptimizer.update": { "total": 711.4164770590814, "count": 68382, "self": 711.4164770590814 } } } } } } }, "trainer_threads": { "total": 1.6049998521339148e-06, "count": 1, "self": 1.6049998521339148e-06 }, "TrainerController._save_models": { "total": 0.12036506699951133, "count": 1, "self": 0.0013524699988920474, "children": { "RLTrainer._checkpoint": { "total": 0.11901259700061928, "count": 1, "self": 0.11901259700061928 } } } } } } }