{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3977733254432678, "min": 0.37277719378471375, "max": 1.4220285415649414, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11850.462890625, "min": 11296.6396484375, "max": 43138.65625, "count": 33 }, "Pyramids.Step.mean": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5039931535720825, "min": -0.11159323155879974, "max": 0.530985951423645, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.0941162109375, "min": -26.78237533569336, "max": 146.02113342285156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0012914410326629877, "min": -0.0021587645169347525, "max": 0.4264684319496155, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.35385483503341675, "min": -0.5785489082336426, "max": 101.0730209350586, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06953371538076594, "min": 0.06409436818406297, "max": 0.07403702865260475, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9734720153307231, "min": 0.5081177427919833, "max": 1.074659741386616, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016667401109034908, "min": 0.00018179075909723766, "max": 0.016837516981121594, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2333436155264887, "min": 0.0016361168318751388, "max": 0.2357252377357023, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.594726039885712e-06, "min": 7.594726039885712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010632616455839997, "min": 0.00010632616455839997, "max": 0.0031372814542396, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253154285714286, "min": 0.10253154285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354416, "min": 1.3886848, "max": 2.400761, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026290113142857143, "min": 0.00026290113142857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00368061584, "min": 0.00368061584, "max": 0.10460146396, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00851133931428194, "min": 0.008331581018865108, "max": 0.4908316433429718, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11915874481201172, "min": 0.11664213240146637, "max": 3.435821533203125, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 347.253164556962, "min": 339.7586206896552, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27433.0, "min": 15984.0, "max": 32636.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5767695949047427, "min": -1.0000000521540642, "max": 1.5767695949047427, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.56479799747467, "min": -32.000001668930054, "max": 138.19279792904854, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5767695949047427, "min": -1.0000000521540642, "max": 1.5767695949047427, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.56479799747467, "min": -32.000001668930054, "max": 138.19279792904854, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030701541991703968, "min": 0.030701541991703968, "max": 11.053673522546887, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4254218173446134, "min": 2.4254218173446134, "max": 176.8587763607502, "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": "1681225101", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681227295" }, "total": 2193.733116587, "count": 1, "self": 0.575332120999974, "children": { "run_training.setup": { "total": 0.1814424469998812, "count": 1, "self": 0.1814424469998812 }, "TrainerController.start_learning": { "total": 2192.976342019, "count": 1, "self": 1.5042649239926504, "children": { "TrainerController._reset_env": { "total": 4.382452587999978, "count": 1, "self": 4.382452587999978 }, "TrainerController.advance": { "total": 2186.9947176930073, "count": 63678, "self": 1.653029699066792, "children": { "env_step": { "total": 1563.7389562269984, "count": 63678, "self": 1448.477523803065, "children": { "SubprocessEnvManager._take_step": { "total": 114.33729148094858, "count": 63678, "self": 5.04914674798988, "children": { "TorchPolicy.evaluate": { "total": 109.2881447329587, "count": 62566, "self": 109.2881447329587 } } }, "workers": { "total": 0.9241409429848773, "count": 63678, "self": 0.0, "children": { "worker_root": { "total": 2187.7216089209883, "count": 63678, "is_parallel": true, "self": 858.2010850369795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030578029998196143, "count": 1, "is_parallel": true, "self": 0.0009982389997276186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020595640000919957, "count": 8, "is_parallel": true, "self": 0.0020595640000919957 } } }, "UnityEnvironment.step": { "total": 0.04966432999981407, "count": 1, "is_parallel": true, "self": 0.0005866100000275765, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005080579999230395, "count": 1, "is_parallel": true, "self": 0.0005080579999230395 }, "communicator.exchange": { "total": 0.04676543099981245, "count": 1, "is_parallel": true, "self": 0.04676543099981245 }, "steps_from_proto": { "total": 0.0018042310000510042, "count": 1, "is_parallel": true, "self": 0.00043109100033689174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013731399997141125, "count": 8, "is_parallel": true, "self": 0.0013731399997141125 } } } } } } }, "UnityEnvironment.step": { "total": 1329.5205238840088, "count": 63677, "is_parallel": true, "self": 33.38039548008828, "children": { "UnityEnvironment._generate_step_input": { "total": 25.140537365961336, "count": 63677, "is_parallel": true, "self": 25.140537365961336 }, "communicator.exchange": { "total": 1169.9754168990123, "count": 63677, "is_parallel": true, "self": 1169.9754168990123 }, "steps_from_proto": { "total": 101.02417413894682, "count": 63677, "is_parallel": true, "self": 22.087353049635567, "children": { "_process_rank_one_or_two_observation": { "total": 78.93682108931125, "count": 509416, "is_parallel": true, "self": 78.93682108931125 } } } } } } } } } } }, "trainer_advance": { "total": 621.6027317669423, "count": 63678, "self": 2.650257457992666, "children": { "process_trajectory": { "total": 112.31786539095492, "count": 63678, "self": 112.11236768095478, "children": { "RLTrainer._checkpoint": { "total": 0.20549771000014516, "count": 2, "self": 0.20549771000014516 } } }, "_update_policy": { "total": 506.6346089179947, "count": 434, "self": 323.07957731999113, "children": { "TorchPPOOptimizer.update": { "total": 183.55503159800355, "count": 22851, "self": 183.55503159800355 } } } } } } }, "trainer_threads": { "total": 1.0110002222063486e-06, "count": 1, "self": 1.0110002222063486e-06 }, "TrainerController._save_models": { "total": 0.09490580300007423, "count": 1, "self": 0.001608506000138732, "children": { "RLTrainer._checkpoint": { "total": 0.0932972969999355, "count": 1, "self": 0.0932972969999355 } } } } } } }