{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45337778329849243, "min": 0.45337778329849243, "max": 1.4459898471832275, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13579.5712890625, "min": 13579.5712890625, "max": 43865.546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4047192335128784, "min": -0.10769429057836533, "max": 0.42652279138565063, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.46475219726562, "min": -26.16971206665039, "max": 114.30810546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004918779246509075, "min": -0.011400463059544563, "max": 0.40535178780555725, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3182328939437866, "min": -3.0325231552124023, "max": 96.06837463378906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07056551573785126, "min": 0.06444140027985781, "max": 0.07428677535722678, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0584827360677689, "min": 0.5088646117833325, "max": 1.082707608966659, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01582521658581552, "min": 0.00015461617455306097, "max": 0.01582521658581552, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2373782487872328, "min": 0.0020100102691897924, "max": 0.2373782487872328, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.560977479706667e-06, "min": 7.560977479706667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011341466219560001, "min": 0.00011341466219560001, "max": 0.0034919005360332, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252029333333333, "min": 0.10252029333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378044, "min": 1.3886848, "max": 2.4639668, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026177730400000007, "min": 0.00026177730400000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003926659560000001, "min": 0.003926659560000001, "max": 0.11641028332, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009095985442399979, "min": 0.008745396509766579, "max": 0.3661887049674988, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13643978536128998, "min": 0.1224355548620224, "max": 2.5633208751678467, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 413.05970149253733, "min": 413.05970149253733, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27675.0, "min": 15984.0, "max": 33903.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4366636102398236, "min": -1.0000000521540642, "max": 1.4366636102398236, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 94.81979827582836, "min": -31.995201647281647, "max": 101.60499835014343, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4366636102398236, "min": -1.0000000521540642, "max": 1.4366636102398236, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 94.81979827582836, "min": -31.995201647281647, "max": 101.60499835014343, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038740578888047654, "min": 0.03868145177289585, "max": 7.478278869763017, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5568782066111453, "min": 2.5568782066111453, "max": 119.65246191620827, "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": "1741203537", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/home/kraz/Documents/DeepRLCourse/ml-agents/VENV/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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741204855" }, "total": 1317.968473361, "count": 1, "self": 0.2690927040002862, "children": { "run_training.setup": { "total": 0.013954913999896235, "count": 1, "self": 0.013954913999896235 }, "TrainerController.start_learning": { "total": 1317.6854257429998, "count": 1, "self": 0.8415892370196616, "children": { "TrainerController._reset_env": { "total": 1.5151184090000243, "count": 1, "self": 1.5151184090000243 }, "TrainerController.advance": { "total": 1315.2693330819798, "count": 63438, "self": 0.8165599330429814, "children": { "env_step": { "total": 860.8822631099536, "count": 63438, "self": 761.0568589329214, "children": { "SubprocessEnvManager._take_step": { "total": 99.28559918407996, "count": 63438, "self": 2.346536811041233, "children": { "TorchPolicy.evaluate": { "total": 96.93906237303872, "count": 62562, "self": 96.93906237303872 } } }, "workers": { "total": 0.5398049929522131, "count": 63438, "self": 0.0, "children": { "worker_root": { "total": 1316.1398561559802, "count": 63438, "is_parallel": true, "self": 619.9053040199549, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011836020000828285, "count": 1, "is_parallel": true, "self": 0.00031521199980488745, "children": { "_process_rank_one_or_two_observation": { "total": 0.000868390000277941, "count": 8, "is_parallel": true, "self": 0.000868390000277941 } } }, "UnityEnvironment.step": { "total": 0.022986456999888105, "count": 1, "is_parallel": true, "self": 0.0002501189999293274, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003391269999610813, "count": 1, "is_parallel": true, "self": 0.0003391269999610813 }, "communicator.exchange": { "total": 0.02166052799998397, "count": 1, "is_parallel": true, "self": 0.02166052799998397 }, "steps_from_proto": { "total": 0.000736683000013727, "count": 1, "is_parallel": true, "self": 0.0002028720000453177, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005338109999684093, "count": 8, "is_parallel": true, "self": 0.0005338109999684093 } } } } } } }, "UnityEnvironment.step": { "total": 696.2345521360253, "count": 63437, "is_parallel": true, "self": 23.863808253042407, "children": { "UnityEnvironment._generate_step_input": { "total": 15.566934434020595, "count": 63437, "is_parallel": true, "self": 15.566934434020595 }, "communicator.exchange": { "total": 594.1222001349615, "count": 63437, "is_parallel": true, "self": 594.1222001349615 }, "steps_from_proto": { "total": 62.68160931400075, "count": 63437, "is_parallel": true, "self": 12.508354508128377, "children": { "_process_rank_one_or_two_observation": { "total": 50.173254805872375, "count": 507496, "is_parallel": true, "self": 50.173254805872375 } } } } } } } } } } }, "trainer_advance": { "total": 453.57051003898323, "count": 63438, "self": 1.4379415429164055, "children": { "process_trajectory": { "total": 74.6194224870676, "count": 63438, "self": 74.47729875106756, "children": { "RLTrainer._checkpoint": { "total": 0.14212373600003048, "count": 2, "self": 0.14212373600003048 } } }, "_update_policy": { "total": 377.51314600899923, "count": 446, "self": 199.6025343140136, "children": { "TorchPPOOptimizer.update": { "total": 177.91061169498562, "count": 22803, "self": 177.91061169498562 } } } } } } }, "trainer_threads": { "total": 5.510000846697949e-07, "count": 1, "self": 5.510000846697949e-07 }, "TrainerController._save_models": { "total": 0.059384464000231674, "count": 1, "self": 0.0011513720000948524, "children": { "RLTrainer._checkpoint": { "total": 0.05823309200013682, "count": 1, "self": 0.05823309200013682 } } } } } } }