{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33852481842041016, "min": 0.3153407573699951, "max": 1.4387987852096558, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10209.908203125, "min": 9394.6318359375, "max": 43647.3984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5344885587692261, "min": -0.08264683932065964, "max": 0.5882424712181091, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.122314453125, "min": -19.917888641357422, "max": 163.53140258789062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.018175538629293442, "min": -0.018175538629293442, "max": 0.35599997639656067, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.070975303649902, "min": -5.070975303649902, "max": 84.37199401855469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06910028079349688, "min": 0.06306291367532228, "max": 0.0743685398641913, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9674039311089563, "min": 0.5016884764269377, "max": 1.1155280979628694, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016959529101450117, "min": 0.0006104015209538778, "max": 0.016959529101450117, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2374334074203016, "min": 0.007935219772400411, "max": 0.2374334074203016, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.168661896192865e-06, "min": 7.168661896192865e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001003612665467001, "min": 0.0001003612665467001, "max": 0.0035069852310049996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10238952142857145, "min": 0.10238952142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4334533000000003, "min": 1.3691136000000002, "max": 2.568995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00024871319071428596, "min": 0.00024871319071428596, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0034819846700000034, "min": 0.0034819846700000034, "max": 0.11692260050000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009281562641263008, "min": 0.008878598921000957, "max": 0.2992088496685028, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1299418807029724, "min": 0.12430039048194885, "max": 2.0944619178771973, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.4886363636364, "min": 327.92134831460675, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30315.0, "min": 15984.0, "max": 32698.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.609842673613784, "min": -1.0000000521540642, "max": 1.609842673613784, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 143.27599795162678, "min": -32.000001668930054, "max": 143.27599795162678, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.609842673613784, "min": -1.0000000521540642, "max": 1.609842673613784, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 143.27599795162678, "min": -32.000001668930054, "max": 143.27599795162678, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03274759279401827, "min": 0.03188862334714491, "max": 6.3722557737492025, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9145357586676255, "min": 2.7081964314565994, "max": 101.95609237998724, "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": "1736418042", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736420292" }, "total": 2249.345509143, "count": 1, "self": 0.9421367810000447, "children": { "run_training.setup": { "total": 0.056301530999917304, "count": 1, "self": 0.056301530999917304 }, "TrainerController.start_learning": { "total": 2248.347070831, "count": 1, "self": 1.4493291869753193, "children": { "TrainerController._reset_env": { "total": 2.270840334000013, "count": 1, "self": 2.270840334000013 }, "TrainerController.advance": { "total": 2244.4985657470247, "count": 63842, "self": 1.4512810020887628, "children": { "env_step": { "total": 1532.6146606799723, "count": 63842, "self": 1378.605828986913, "children": { "SubprocessEnvManager._take_step": { "total": 153.16004045703983, "count": 63842, "self": 4.786850186041306, "children": { "TorchPolicy.evaluate": { "total": 148.37319027099852, "count": 62543, "self": 148.37319027099852 } } }, "workers": { "total": 0.8487912360194514, "count": 63842, "self": 0.0, "children": { "worker_root": { "total": 2243.378669524005, "count": 63842, "is_parallel": true, "self": 984.7692908670299, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019776830000637347, "count": 1, "is_parallel": true, "self": 0.0006333070001574015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013443759999063332, "count": 8, "is_parallel": true, "self": 0.0013443759999063332 } } }, "UnityEnvironment.step": { "total": 0.04914357999996355, "count": 1, "is_parallel": true, "self": 0.000710049999952389, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044925199995304865, "count": 1, "is_parallel": true, "self": 0.00044925199995304865 }, "communicator.exchange": { "total": 0.04617469400000118, "count": 1, "is_parallel": true, "self": 0.04617469400000118 }, "steps_from_proto": { "total": 0.0018095840000569297, "count": 1, "is_parallel": true, "self": 0.0003805420000162485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014290420000406812, "count": 8, "is_parallel": true, "self": 0.0014290420000406812 } } } } } } }, "UnityEnvironment.step": { "total": 1258.6093786569752, "count": 63841, "is_parallel": true, "self": 33.72061371803443, "children": { "UnityEnvironment._generate_step_input": { "total": 23.121119736962896, "count": 63841, "is_parallel": true, "self": 23.121119736962896 }, "communicator.exchange": { "total": 1102.4336031819364, "count": 63841, "is_parallel": true, "self": 1102.4336031819364 }, "steps_from_proto": { "total": 99.33404202004158, "count": 63841, "is_parallel": true, "self": 20.21092110911013, "children": { "_process_rank_one_or_two_observation": { "total": 79.12312091093145, "count": 510728, "is_parallel": true, "self": 79.12312091093145 } } } } } } } } } } }, "trainer_advance": { "total": 710.4326240649638, "count": 63842, "self": 2.8619799989792227, "children": { "process_trajectory": { "total": 135.76293144298006, "count": 63842, "self": 135.4763563369802, "children": { "RLTrainer._checkpoint": { "total": 0.2865751059998729, "count": 2, "self": 0.2865751059998729 } } }, "_update_policy": { "total": 571.8077126230045, "count": 447, "self": 321.25722820901103, "children": { "TorchPPOOptimizer.update": { "total": 250.55048441399344, "count": 22812, "self": 250.55048441399344 } } } } } } }, "trainer_threads": { "total": 1.4090001059230417e-06, "count": 1, "self": 1.4090001059230417e-06 }, "TrainerController._save_models": { "total": 0.12833415400018566, "count": 1, "self": 0.0020799970002371992, "children": { "RLTrainer._checkpoint": { "total": 0.12625415699994846, "count": 1, "self": 0.12625415699994846 } } } } } } }