{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.26455119252204895, "min": 0.25730034708976746, "max": 1.4268423318862915, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7801.08544921875, "min": 7735.4775390625, "max": 43284.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29921.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29921.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6805106997489929, "min": -0.14318153262138367, "max": 0.7332727909088135, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 192.58453369140625, "min": -33.934024810791016, "max": 212.64910888671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02383018285036087, "min": -0.024618465453386307, "max": 0.5752167701721191, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.743941783905029, "min": -6.991644382476807, "max": 136.3263702392578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06555478800296649, "min": 0.06473996133143435, "max": 0.07239833208946679, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9833218200444974, "min": 0.5192019820769689, "max": 1.068259297501451, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015947737734843946, "min": 0.0010392412391381244, "max": 0.015960494290560574, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2392160660226592, "min": 0.014549377347933743, "max": 0.2392160660226592, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.491737502786662e-06, "min": 7.491737502786662e-06, "max": 0.000295285876571375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011237606254179993, "min": 0.00011237606254179993, "max": 0.0036333859888713995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249721333333334, "min": 0.10249721333333334, "max": 0.19842862500000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374582, "min": 1.4778726000000002, "max": 2.6111286000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002594716119999999, "min": 0.0002594716119999999, "max": 0.009843019637500002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003892074179999998, "min": 0.003892074179999998, "max": 0.12113174714, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01397061999887228, "min": 0.01397061999887228, "max": 0.5137081146240234, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20955930650234222, "min": 0.2025238275527954, "max": 4.1096649169921875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 278.375, "min": 259.57272727272726, "max": 992.96875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28951.0, "min": 16592.0, "max": 32712.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6831557524318879, "min": -0.931275051087141, "max": 1.740427260642702, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.04819825291634, "min": -29.800801634788513, "max": 191.4469986706972, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6831557524318879, "min": -0.931275051087141, "max": 1.740427260642702, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.04819825291634, "min": -29.800801634788513, "max": 191.4469986706972, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0398771760236951, "min": 0.039678632874645035, "max": 9.751603273784413, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.14722630646429, "min": 4.14722630646429, "max": 165.77725565433502, "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": "1673478864", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673480887" }, "total": 2022.8612759880002, "count": 1, "self": 0.4746048189999783, "children": { "run_training.setup": { "total": 0.1027661610000905, "count": 1, "self": 0.1027661610000905 }, "TrainerController.start_learning": { "total": 2022.2839050080001, "count": 1, "self": 1.234698234008647, "children": { "TrainerController._reset_env": { "total": 6.423264372000176, "count": 1, "self": 6.423264372000176 }, "TrainerController.advance": { "total": 2014.5422596019912, "count": 64175, "self": 1.242534436142705, "children": { "env_step": { "total": 1357.8303052819451, "count": 64175, "self": 1255.3417347438458, "children": { "SubprocessEnvManager._take_step": { "total": 101.725861048973, "count": 64175, "self": 4.153576772963788, "children": { "TorchPolicy.evaluate": { "total": 97.57228427600921, "count": 62542, "self": 32.70095403597634, "children": { "TorchPolicy.sample_actions": { "total": 64.87133024003288, "count": 62542, "self": 64.87133024003288 } } } } }, "workers": { "total": 0.7627094891263368, "count": 64175, "self": 0.0, "children": { "worker_root": { "total": 2017.8959287260964, "count": 64175, "is_parallel": true, "self": 858.5676505691308, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016614609999123786, "count": 1, "is_parallel": true, "self": 0.0005746369993175904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010868240005947882, "count": 8, "is_parallel": true, "self": 0.0010868240005947882 } } }, "UnityEnvironment.step": { "total": 0.044122803999925964, "count": 1, "is_parallel": true, "self": 0.00048708300028010854, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004120169996895129, "count": 1, "is_parallel": true, "self": 0.0004120169996895129 }, "communicator.exchange": { "total": 0.041665663000003406, "count": 1, "is_parallel": true, "self": 0.041665663000003406 }, "steps_from_proto": { "total": 0.0015580409999529365, "count": 1, "is_parallel": true, "self": 0.0004140250002819812, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011440159996709554, "count": 8, "is_parallel": true, "self": 0.0011440159996709554 } } } } } } }, "UnityEnvironment.step": { "total": 1159.3282781569656, "count": 64174, "is_parallel": true, "self": 27.049934242840664, "children": { "UnityEnvironment._generate_step_input": { "total": 21.37176819603519, "count": 64174, "is_parallel": true, "self": 21.37176819603519 }, "communicator.exchange": { "total": 1013.6972810630455, "count": 64174, "is_parallel": true, "self": 1013.6972810630455 }, "steps_from_proto": { "total": 97.20929465504423, "count": 64174, "is_parallel": true, "self": 21.036556927196216, "children": { "_process_rank_one_or_two_observation": { "total": 76.17273772784802, "count": 513392, "is_parallel": true, "self": 76.17273772784802 } } } } } } } } } } }, "trainer_advance": { "total": 655.4694198839034, "count": 64175, "self": 2.35511943394431, "children": { "process_trajectory": { "total": 145.31231152596138, "count": 64175, "self": 145.11273293196155, "children": { "RLTrainer._checkpoint": { "total": 0.19957859399983136, "count": 2, "self": 0.19957859399983136 } } }, "_update_policy": { "total": 507.80198892399767, "count": 455, "self": 193.7009492519669, "children": { "TorchPPOOptimizer.update": { "total": 314.10103967203077, "count": 22764, "self": 314.10103967203077 } } } } } } }, "trainer_threads": { "total": 8.910001270123757e-07, "count": 1, "self": 8.910001270123757e-07 }, "TrainerController._save_models": { "total": 0.08368190900000627, "count": 1, "self": 0.001352815000245755, "children": { "RLTrainer._checkpoint": { "total": 0.08232909399976052, "count": 1, "self": 0.08232909399976052 } } } } } } }