{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4398382008075714, "min": 0.4238719940185547, "max": 1.364965796470642, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13251.4453125, "min": 12702.595703125, "max": 41407.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29900.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29900.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1341107189655304, "min": -0.09329152852296829, "max": 0.2606421113014221, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 33.66178894042969, "min": -22.576549530029297, "max": 67.76695251464844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.20094819366931915, "min": -0.5484257936477661, "max": 1.098501443862915, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -50.43799591064453, "min": -140.39700317382812, "max": 265.83734130859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.028851296392358127, "min": 0.026597161497366396, "max": 0.03466776526795748, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.4039181494930138, "min": 0.2408306985245352, "max": 0.5013927734301735, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02562788784936337, "min": 0.001251932295983554, "max": 0.08690441572772604, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.35879042989108717, "min": 0.01877898443975331, "max": 1.2166618201881647, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.816340251728574e-06, "min": 7.816340251728574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010942876352420004, "min": 0.00010942876352420004, "max": 0.0036328261890579997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10260541428571426, "min": 0.10260541428571426, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4364757999999997, "min": 1.3886848, "max": 2.610942, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002702808871428573, "min": 0.0002702808871428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003783932420000002, "min": 0.003783932420000002, "max": 0.12111310580000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.034021418541669846, "min": 0.034021418541669846, "max": 1.4695684909820557, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.47629988193511963, "min": 0.47629988193511963, "max": 10.286979675292969, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 732.5714285714286, "min": 580.0384615384615, "max": 989.8235294117648, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30768.0, "min": 16827.0, "max": 32939.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6005952129406589, "min": -0.8731177010956932, "max": 1.1308510281304096, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 25.22499894350767, "min": -28.142201617360115, "max": 53.14999832212925, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6005952129406589, "min": -0.8731177010956932, "max": 1.1308510281304096, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 25.22499894350767, "min": -28.142201617360115, "max": 53.14999832212925, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.25056493466365193, "min": 0.25056493466365193, "max": 14.99167394988677, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 10.523727255873382, "min": 10.523727255873382, "max": 441.9088951051235, "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": "1684193510", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684195335" }, "total": 1825.5639480539999, "count": 1, "self": 1.1941218739998476, "children": { "run_training.setup": { "total": 0.050843851000081486, "count": 1, "self": 0.050843851000081486 }, "TrainerController.start_learning": { "total": 1824.318982329, "count": 1, "self": 1.2847260070084303, "children": { "TrainerController._reset_env": { "total": 3.7231513050001013, "count": 1, "self": 3.7231513050001013 }, "TrainerController.advance": { "total": 1819.1672743579911, "count": 63424, "self": 1.3020664529790338, "children": { "env_step": { "total": 1366.015843351991, "count": 63424, "self": 1257.4835447318997, "children": { "SubprocessEnvManager._take_step": { "total": 107.74377267808131, "count": 63424, "self": 4.607415990043137, "children": { "TorchPolicy.evaluate": { "total": 103.13635668803818, "count": 62555, "self": 103.13635668803818 } } }, "workers": { "total": 0.7885259420099828, "count": 63424, "self": 0.0, "children": { "worker_root": { "total": 1819.6278105629822, "count": 63424, "is_parallel": true, "self": 669.4823963439876, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018231219996778236, "count": 1, "is_parallel": true, "self": 0.000553677999505453, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012694440001723706, "count": 8, "is_parallel": true, "self": 0.0012694440001723706 } } }, "UnityEnvironment.step": { "total": 0.045019358999979886, "count": 1, "is_parallel": true, "self": 0.0005261120004433906, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004858139996031241, "count": 1, "is_parallel": true, "self": 0.0004858139996031241 }, "communicator.exchange": { "total": 0.04223898400005055, "count": 1, "is_parallel": true, "self": 0.04223898400005055 }, "steps_from_proto": { "total": 0.0017684489998828212, "count": 1, "is_parallel": true, "self": 0.0003692109994517523, "children": { "_process_rank_one_or_two_observation": { "total": 0.001399238000431069, "count": 8, "is_parallel": true, "self": 0.001399238000431069 } } } } } } }, "UnityEnvironment.step": { "total": 1150.1454142189946, "count": 63423, "is_parallel": true, "self": 31.11015229206305, "children": { "UnityEnvironment._generate_step_input": { "total": 22.89645160395139, "count": 63423, "is_parallel": true, "self": 22.89645160395139 }, "communicator.exchange": { "total": 999.3612651640324, "count": 63423, "is_parallel": true, "self": 999.3612651640324 }, "steps_from_proto": { "total": 96.77754515894776, "count": 63423, "is_parallel": true, "self": 19.473607182837895, "children": { "_process_rank_one_or_two_observation": { "total": 77.30393797610986, "count": 507384, "is_parallel": true, "self": 77.30393797610986 } } } } } } } } } } }, "trainer_advance": { "total": 451.84936455302113, "count": 63424, "self": 2.524590062030711, "children": { "process_trajectory": { "total": 104.64860921499167, "count": 63424, "self": 104.39735654899187, "children": { "RLTrainer._checkpoint": { "total": 0.25125266599980023, "count": 2, "self": 0.25125266599980023 } } }, "_update_policy": { "total": 344.67616527599876, "count": 456, "self": 283.13469027999054, "children": { "TorchPPOOptimizer.update": { "total": 61.54147499600822, "count": 5622, "self": 61.54147499600822 } } } } } } }, "trainer_threads": { "total": 1.3270000636111945e-06, "count": 1, "self": 1.3270000636111945e-06 }, "TrainerController._save_models": { "total": 0.14382933200022308, "count": 1, "self": 0.001924471000165795, "children": { "RLTrainer._checkpoint": { "total": 0.14190486100005728, "count": 1, "self": 0.14190486100005728 } } } } } } }