{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28620773553848267, "min": 0.28620773553848267, "max": 1.3941848278045654, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8714.453125, "min": 8714.453125, "max": 42293.9921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5719218254089355, "min": -0.14826145768165588, "max": 0.6345453262329102, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.1381072998047, "min": -36.02753448486328, "max": 180.21087646484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015681233257055283, "min": -0.004872321616858244, "max": 0.342519074678421, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.390745162963867, "min": -1.344760775566101, "max": 81.17701721191406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06947490652410558, "min": 0.06514014818357351, "max": 0.07274604728706287, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9726486913374781, "min": 0.48159459436693003, "max": 1.0720746292305798, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018775865997581388, "min": 0.000894337887281473, "max": 0.018775865997581388, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26286212396613945, "min": 0.006260365210970311, "max": 0.266711541118817, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.522447492550002e-06, "min": 7.522447492550002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010531426489570004, "min": 0.00010531426489570004, "max": 0.0036297100900966996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250745000000001, "min": 0.10250745000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351043, "min": 1.3691136000000002, "max": 2.6099033, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002604942550000001, "min": 0.0002604942550000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003646919570000002, "min": 0.003646919570000002, "max": 0.12100933967, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008779570460319519, "min": 0.008779570460319519, "max": 0.4866790473461151, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12291398644447327, "min": 0.12291398644447327, "max": 3.4067533016204834, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 304.53921568627453, "min": 299.28, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31063.0, "min": 15984.0, "max": 32799.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6534058641569287, "min": -1.0000000521540642, "max": 1.6843711160814638, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.64739814400673, "min": -32.000001668930054, "max": 168.64739814400673, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6534058641569287, "min": -1.0000000521540642, "max": 1.6843711160814638, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.64739814400673, "min": -32.000001668930054, "max": 168.64739814400673, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027961951244637306, "min": 0.027866449126811473, "max": 9.934462127275765, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8521190269530052, "min": 2.7587784635543358, "max": 158.95139403641224, "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": "1688437116", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688439401" }, "total": 2285.401040783, "count": 1, "self": 0.5743434069991054, "children": { "run_training.setup": { "total": 0.03895458600072743, "count": 1, "self": 0.03895458600072743 }, "TrainerController.start_learning": { "total": 2284.7877427900003, "count": 1, "self": 1.5547518311987005, "children": { "TrainerController._reset_env": { "total": 4.099468727000385, "count": 1, "self": 4.099468727000385 }, "TrainerController.advance": { "total": 2279.0367745638014, "count": 64225, "self": 1.5034287967519049, "children": { "env_step": { "total": 1639.1270037220656, "count": 64225, "self": 1524.992937074091, "children": { "SubprocessEnvManager._take_step": { "total": 113.25343436896947, "count": 64225, "self": 4.9004074259019035, "children": { "TorchPolicy.evaluate": { "total": 108.35302694306756, "count": 62577, "self": 108.35302694306756 } } }, "workers": { "total": 0.8806322790051127, "count": 64225, "self": 0.0, "children": { "worker_root": { "total": 2279.406570759974, "count": 64225, "is_parallel": true, "self": 871.6023004190502, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001737641000545409, "count": 1, "is_parallel": true, "self": 0.0005288530010147952, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012087879995306139, "count": 8, "is_parallel": true, "self": 0.0012087879995306139 } } }, "UnityEnvironment.step": { "total": 0.04626485600056185, "count": 1, "is_parallel": true, "self": 0.0005396070000642794, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048086399965541204, "count": 1, "is_parallel": true, "self": 0.00048086399965541204 }, "communicator.exchange": { "total": 0.04344958800083987, "count": 1, "is_parallel": true, "self": 0.04344958800083987 }, "steps_from_proto": { "total": 0.0017947970000022906, "count": 1, "is_parallel": true, "self": 0.00035787800061370945, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014369189993885811, "count": 8, "is_parallel": true, "self": 0.0014369189993885811 } } } } } } }, "UnityEnvironment.step": { "total": 1407.8042703409237, "count": 64224, "is_parallel": true, "self": 33.37613834170497, "children": { "UnityEnvironment._generate_step_input": { "total": 22.74970432221926, "count": 64224, "is_parallel": true, "self": 22.74970432221926 }, "communicator.exchange": { "total": 1250.1854122220393, "count": 64224, "is_parallel": true, "self": 1250.1854122220393 }, "steps_from_proto": { "total": 101.49301545496019, "count": 64224, "is_parallel": true, "self": 20.34488065082951, "children": { "_process_rank_one_or_two_observation": { "total": 81.14813480413068, "count": 513792, "is_parallel": true, "self": 81.14813480413068 } } } } } } } } } } }, "trainer_advance": { "total": 638.4063420449838, "count": 64225, "self": 2.895981084860068, "children": { "process_trajectory": { "total": 109.84948761712621, "count": 64225, "self": 109.64794533112581, "children": { "RLTrainer._checkpoint": { "total": 0.2015422860004037, "count": 2, "self": 0.2015422860004037 } } }, "_update_policy": { "total": 525.6608733429975, "count": 453, "self": 336.18082120103736, "children": { "TorchPPOOptimizer.update": { "total": 189.4800521419602, "count": 22824, "self": 189.4800521419602 } } } } } } }, "trainer_threads": { "total": 1.2749997040373273e-06, "count": 1, "self": 1.2749997040373273e-06 }, "TrainerController._save_models": { "total": 0.09674639300010313, "count": 1, "self": 0.0014335819996631471, "children": { "RLTrainer._checkpoint": { "total": 0.09531281100043998, "count": 1, "self": 0.09531281100043998 } } } } } } }