{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4669658839702606, "min": 0.461290568113327, "max": 1.4188251495361328, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13807.2470703125, "min": 13776.451171875, "max": 43041.48046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989904.0, "min": 29892.0, "max": 989904.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989904.0, "min": 29892.0, "max": 989904.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4073258638381958, "min": -0.10119510442018509, "max": 0.46450650691986084, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 109.163330078125, "min": -24.489215850830078, "max": 124.48774719238281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.21192243695259094, "min": -0.21192243695259094, "max": 0.21247458457946777, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -56.79521179199219, "min": -56.79521179199219, "max": 53.14268112182617, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06875272933878782, "min": 0.06472302721387252, "max": 0.07243377668783067, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9625382107430294, "min": 0.5743501324011824, "max": 1.0468199020103262, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01730627357132367, "min": 0.0002818444567268246, "max": 0.018975873017924607, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24228782999853138, "min": 0.00366397793744872, "max": 0.2656622222509445, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.689226008385715e-06, "min": 7.689226008385715e-06, "max": 0.00029521695159435, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010764916411740001, "min": 0.00010764916411740001, "max": 0.0034934272355243, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256304285714286, "min": 0.10256304285714286, "max": 0.19840565, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358826, "min": 1.4358826, "max": 2.4825325, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002660479814285715, "min": 0.0002660479814285715, "max": 0.009840724435, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003724671740000001, "min": 0.003724671740000001, "max": 0.11646112243, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008709762245416641, "min": 0.008588920347392559, "max": 0.33532604575157166, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12193667143583298, "min": 0.12024489045143127, "max": 2.6826083660125732, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 416.49295774647885, "min": 397.3918918918919, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29571.0, "min": 15924.0, "max": 33120.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.307769421591527, "min": -0.999860051771005, "max": 1.4773351125217773, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 94.15939835458994, "min": -30.352801650762558, "max": 109.32279832661152, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.307769421591527, "min": -0.999860051771005, "max": 1.4773351125217773, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 94.15939835458994, "min": -30.352801650762558, "max": 109.32279832661152, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03791579846458464, "min": 0.03791579846458464, "max": 6.711422516033053, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7299374894500943, "min": 2.6124265679973178, "max": 107.38276025652885, "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": "1700416329", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700418746" }, "total": 2417.823263444, "count": 1, "self": 0.48219893900022726, "children": { "run_training.setup": { "total": 0.06870605900007831, "count": 1, "self": 0.06870605900007831 }, "TrainerController.start_learning": { "total": 2417.272358446, "count": 1, "self": 1.646070274026897, "children": { "TrainerController._reset_env": { "total": 4.755365217999952, "count": 1, "self": 4.755365217999952 }, "TrainerController.advance": { "total": 2410.793558915973, "count": 63630, "self": 1.7057529349985998, "children": { "env_step": { "total": 1738.3432255009836, "count": 63630, "self": 1584.7863243200675, "children": { "SubprocessEnvManager._take_step": { "total": 152.4960201949682, "count": 63630, "self": 5.138612344905823, "children": { "TorchPolicy.evaluate": { "total": 147.35740785006237, "count": 62554, "self": 147.35740785006237 } } }, "workers": { "total": 1.0608809859479607, "count": 63630, "self": 0.0, "children": { "worker_root": { "total": 2411.6741630560578, "count": 63630, "is_parallel": true, "self": 965.1641919740614, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026090399999247893, "count": 1, "is_parallel": true, "self": 0.0007674620003399468, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018415779995848425, "count": 8, "is_parallel": true, "self": 0.0018415779995848425 } } }, "UnityEnvironment.step": { "total": 0.05093590299998141, "count": 1, "is_parallel": true, "self": 0.0006002749998970103, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005165430000033666, "count": 1, "is_parallel": true, "self": 0.0005165430000033666 }, "communicator.exchange": { "total": 0.04809122799997567, "count": 1, "is_parallel": true, "self": 0.04809122799997567 }, "steps_from_proto": { "total": 0.0017278570001053595, "count": 1, "is_parallel": true, "self": 0.00037055900020277477, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013572979999025847, "count": 8, "is_parallel": true, "self": 0.0013572979999025847 } } } } } } }, "UnityEnvironment.step": { "total": 1446.5099710819964, "count": 63629, "is_parallel": true, "self": 37.04309107093877, "children": { "UnityEnvironment._generate_step_input": { "total": 26.053372946964373, "count": 63629, "is_parallel": true, "self": 26.053372946964373 }, "communicator.exchange": { "total": 1275.056950830066, "count": 63629, "is_parallel": true, "self": 1275.056950830066 }, "steps_from_proto": { "total": 108.35655623402727, "count": 63629, "is_parallel": true, "self": 22.948075308865327, "children": { "_process_rank_one_or_two_observation": { "total": 85.40848092516194, "count": 509032, "is_parallel": true, "self": 85.40848092516194 } } } } } } } } } } }, "trainer_advance": { "total": 670.7445804799906, "count": 63630, "self": 3.231416617028799, "children": { "process_trajectory": { "total": 137.943789966964, "count": 63630, "self": 137.77992008496426, "children": { "RLTrainer._checkpoint": { "total": 0.1638698819997444, "count": 2, "self": 0.1638698819997444 } } }, "_update_policy": { "total": 529.5693738959978, "count": 453, "self": 314.8333891949803, "children": { "TorchPPOOptimizer.update": { "total": 214.73598470101751, "count": 22803, "self": 214.73598470101751 } } } } } } }, "trainer_threads": { "total": 1.0839999049494509e-06, "count": 1, "self": 1.0839999049494509e-06 }, "TrainerController._save_models": { "total": 0.07736295400036397, "count": 1, "self": 0.0013060510004834214, "children": { "RLTrainer._checkpoint": { "total": 0.07605690299988055, "count": 1, "self": 0.07605690299988055 } } } } } } }