{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4070066511631012, "min": 0.4021722674369812, "max": 1.3479180335998535, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12171.126953125, "min": 12052.298828125, "max": 40890.44140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.13684844970703125, "min": -0.0993741974234581, "max": 0.13684844970703125, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 34.485809326171875, "min": -24.048555374145508, "max": 34.485809326171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011632637120783329, "min": 0.01112455129623413, "max": 0.5499749183654785, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.931424617767334, "min": 2.7477641105651855, "max": 130.34405517578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06958726002816476, "min": 0.06692128362507985, "max": 0.07867150353943533, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9742216403943067, "min": 0.5507005247760474, "max": 1.0281149565736425, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008634864743196309, "min": 0.0006697984183612096, "max": 0.07630209713278313, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12088810640474833, "min": 0.008752896569352039, "max": 0.5341146799294819, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.688476008635716e-06, "min": 7.688476008635716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010763866412090003, "min": 0.00010763866412090003, "max": 0.0033770014743328995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256279285714286, "min": 0.10256279285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358791, "min": 1.3886848, "max": 2.4441323000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002660230064285715, "min": 0.0002660230064285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003724322090000001, "min": 0.003724322090000001, "max": 0.11258414328999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02195557951927185, "min": 0.02195557951927185, "max": 0.6353740692138672, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3073781132698059, "min": 0.3073781132698059, "max": 4.44761848449707, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 696.2444444444444, "min": 696.2444444444444, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31331.0, "min": 15984.0, "max": 33154.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5035866328411632, "min": -1.0000000521540642, "max": 0.5697511765288144, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 22.661398477852345, "min": -29.51360158622265, "max": 23.35979823768139, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5035866328411632, "min": -1.0000000521540642, "max": 0.5697511765288144, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 22.661398477852345, "min": -29.51360158622265, "max": 23.35979823768139, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 1.5703007025230262, "min": 1.5703007025230262, "max": 138.3422848880291, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 70.66353161353618, "min": 67.04416026454419, "max": 2213.4765582084656, "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": "1704218689", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704220877" }, "total": 2188.656214685, "count": 1, "self": 0.5400198320003256, "children": { "run_training.setup": { "total": 0.04728582699999606, "count": 1, "self": 0.04728582699999606 }, "TrainerController.start_learning": { "total": 2188.068909026, "count": 1, "self": 1.4711257861117701, "children": { "TrainerController._reset_env": { "total": 2.0432163489999766, "count": 1, "self": 2.0432163489999766 }, "TrainerController.advance": { "total": 2184.466138085888, "count": 63330, "self": 1.484879688800902, "children": { "env_step": { "total": 1538.8759587490586, "count": 63330, "self": 1402.7823609819538, "children": { "SubprocessEnvManager._take_step": { "total": 135.19962338402047, "count": 63330, "self": 5.049654684910365, "children": { "TorchPolicy.evaluate": { "total": 130.1499686991101, "count": 62577, "self": 130.1499686991101 } } }, "workers": { "total": 0.8939743830842417, "count": 63330, "self": 0.0, "children": { "worker_root": { "total": 2182.699190598978, "count": 63330, "is_parallel": true, "self": 906.5549125030211, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001892005000172503, "count": 1, "is_parallel": true, "self": 0.0005875320002814988, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013044729998910043, "count": 8, "is_parallel": true, "self": 0.0013044729998910043 } } }, "UnityEnvironment.step": { "total": 0.054334746999757044, "count": 1, "is_parallel": true, "self": 0.0006469299996751943, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048669700026948703, "count": 1, "is_parallel": true, "self": 0.00048669700026948703 }, "communicator.exchange": { "total": 0.0502278999997543, "count": 1, "is_parallel": true, "self": 0.0502278999997543 }, "steps_from_proto": { "total": 0.0029732200000580633, "count": 1, "is_parallel": true, "self": 0.00039559999959237757, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025776200004656857, "count": 8, "is_parallel": true, "self": 0.0025776200004656857 } } } } } } }, "UnityEnvironment.step": { "total": 1276.144278095957, "count": 63329, "is_parallel": true, "self": 36.3279967767121, "children": { "UnityEnvironment._generate_step_input": { "total": 26.649070108000615, "count": 63329, "is_parallel": true, "self": 26.649070108000615 }, "communicator.exchange": { "total": 1107.4047224351193, "count": 63329, "is_parallel": true, "self": 1107.4047224351193 }, "steps_from_proto": { "total": 105.76248877612488, "count": 63329, "is_parallel": true, "self": 21.99093297650279, "children": { "_process_rank_one_or_two_observation": { "total": 83.77155579962209, "count": 506632, "is_parallel": true, "self": 83.77155579962209 } } } } } } } } } } }, "trainer_advance": { "total": 644.1052996480284, "count": 63330, "self": 2.7831671289677615, "children": { "process_trajectory": { "total": 131.11311800106705, "count": 63330, "self": 130.91421882006762, "children": { "RLTrainer._checkpoint": { "total": 0.19889918099943316, "count": 2, "self": 0.19889918099943316 } } }, "_update_policy": { "total": 510.20901451799364, "count": 450, "self": 303.71846219399686, "children": { "TorchPPOOptimizer.update": { "total": 206.49055232399678, "count": 22809, "self": 206.49055232399678 } } } } } } }, "trainer_threads": { "total": 1.0339999789721332e-06, "count": 1, "self": 1.0339999789721332e-06 }, "TrainerController._save_models": { "total": 0.08842777100016974, "count": 1, "self": 0.001418542000465095, "children": { "RLTrainer._checkpoint": { "total": 0.08700922899970465, "count": 1, "self": 0.08700922899970465 } } } } } } }