{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4087747633457184, "min": 0.4087747633457184, "max": 1.4730157852172852, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12380.9697265625, "min": 12380.9697265625, "max": 44685.40625, "count": 33 }, "Pyramids.Step.mean": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5950990915298462, "min": -0.0900569036602974, "max": 0.6115435361862183, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.22283935546875, "min": -21.79376983642578, "max": 173.67835998535156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.018987886607646942, "min": -0.018987886607646942, "max": 0.4136049151420593, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.335596084594727, "min": -5.335596084594727, "max": 98.02436828613281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06598004386718717, "min": 0.06400465247950776, "max": 0.07409106457869441, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9237206141406203, "min": 0.49821883825158386, "max": 1.0622751194556865, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015419170455840818, "min": 0.0008333816008584832, "max": 0.016253235390606628, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21586838638177144, "min": 0.009426100031247898, "max": 0.24177653466176707, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.733733136407143e-06, "min": 7.733733136407143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010827226390970001, "min": 0.00010827226390970001, "max": 0.0036349339883553996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257787857142857, "min": 0.10257787857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360903, "min": 1.3691136000000002, "max": 2.6116445999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002675300692857144, "min": 0.0002675300692857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003745420970000002, "min": 0.003745420970000002, "max": 0.12118329554, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007969427853822708, "min": 0.007969427853822708, "max": 0.40949440002441406, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11157198995351791, "min": 0.11157198995351791, "max": 2.8664608001708984, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.4782608695652, "min": 306.03061224489795, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31140.0, "min": 15984.0, "max": 34317.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5745325945317745, "min": -1.0000000521540642, "max": 1.6735571162128935, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.85699869692326, "min": -32.000001668930054, "max": 164.00859738886356, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5745325945317745, "min": -1.0000000521540642, "max": 1.6735571162128935, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.85699869692326, "min": -32.000001668930054, "max": 164.00859738886356, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027764228831548953, "min": 0.027764228831548953, "max": 7.693552754819393, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5543090525025036, "min": 2.5282236517232377, "max": 123.09684407711029, "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": "1739094095", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739097430" }, "total": 3334.3070785980003, "count": 1, "self": 0.6998105560001022, "children": { "run_training.setup": { "total": 0.047072504999960074, "count": 1, "self": 0.047072504999960074 }, "TrainerController.start_learning": { "total": 3333.5601955370003, "count": 1, "self": 2.3451455460749457, "children": { "TrainerController._reset_env": { "total": 4.310322269000153, "count": 1, "self": 4.310322269000153 }, "TrainerController.advance": { "total": 3326.817292656926, "count": 63866, "self": 2.6463284409251173, "children": { "env_step": { "total": 2219.935999484886, "count": 63866, "self": 2047.24230951678, "children": { "SubprocessEnvManager._take_step": { "total": 171.28903421707946, "count": 63866, "self": 7.045626418187567, "children": { "TorchPolicy.evaluate": { "total": 164.2434077988919, "count": 62556, "self": 164.2434077988919 } } }, "workers": { "total": 1.4046557510264392, "count": 63866, "self": 0.0, "children": { "worker_root": { "total": 3326.153496971984, "count": 63866, "is_parallel": true, "self": 1457.1016116249157, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00762704799990388, "count": 1, "is_parallel": true, "self": 0.005514737999419594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021123100004842854, "count": 8, "is_parallel": true, "self": 0.0021123100004842854 } } }, "UnityEnvironment.step": { "total": 0.06117395100000067, "count": 1, "is_parallel": true, "self": 0.0006665999999313499, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005294039997352229, "count": 1, "is_parallel": true, "self": 0.0005294039997352229 }, "communicator.exchange": { "total": 0.05789101900018068, "count": 1, "is_parallel": true, "self": 0.05789101900018068 }, "steps_from_proto": { "total": 0.0020869280001534207, "count": 1, "is_parallel": true, "self": 0.0005737240003327315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015132039998206892, "count": 8, "is_parallel": true, "self": 0.0015132039998206892 } } } } } } }, "UnityEnvironment.step": { "total": 1869.0518853470685, "count": 63865, "is_parallel": true, "self": 45.56137264885501, "children": { "UnityEnvironment._generate_step_input": { "total": 30.020402086137437, "count": 63865, "is_parallel": true, "self": 30.020402086137437 }, "communicator.exchange": { "total": 1667.117851420037, "count": 63865, "is_parallel": true, "self": 1667.117851420037 }, "steps_from_proto": { "total": 126.35225919203913, "count": 63865, "is_parallel": true, "self": 27.48234687147442, "children": { "_process_rank_one_or_two_observation": { "total": 98.86991232056471, "count": 510920, "is_parallel": true, "self": 98.86991232056471 } } } } } } } } } } }, "trainer_advance": { "total": 1104.2349647311148, "count": 63866, "self": 4.670243471187405, "children": { "process_trajectory": { "total": 167.42808700592514, "count": 63866, "self": 167.05367645692468, "children": { "RLTrainer._checkpoint": { "total": 0.37441054900045856, "count": 2, "self": 0.37441054900045856 } } }, "_update_policy": { "total": 932.1366342540023, "count": 452, "self": 366.87589921205245, "children": { "TorchPPOOptimizer.update": { "total": 565.2607350419498, "count": 22800, "self": 565.2607350419498 } } } } } } }, "trainer_threads": { "total": 1.0929998097708449e-06, "count": 1, "self": 1.0929998097708449e-06 }, "TrainerController._save_models": { "total": 0.08743397199941683, "count": 1, "self": 0.0021712949992434005, "children": { "RLTrainer._checkpoint": { "total": 0.08526267700017343, "count": 1, "self": 0.08526267700017343 } } } } } } }