{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6159734725952148, "min": 0.6159734725952148, "max": 1.468456506729126, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18735.44921875, "min": 18729.9140625, "max": 44547.09765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.325443834066391, "min": -0.09946846961975098, "max": 0.367620050907135, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 84.94084167480469, "min": -24.071369171142578, "max": 95.9488296508789, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005958512891083956, "min": -0.013418427668511868, "max": 0.29607051610946655, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.5551718473434448, "min": -3.3277699947357178, "max": 71.35299682617188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06862986352574635, "min": 0.06474863332089105, "max": 0.07473892720917169, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9608180893604489, "min": 0.5094420612587636, "max": 1.0232998070530015, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014837119869688262, "min": 0.00023721445484447458, "max": 0.014837119869688262, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20771967817563566, "min": 0.0033210023678226443, "max": 0.21605031687310355, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.693404578421426e-06, "min": 7.693404578421426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010770766409789997, "min": 0.00010770766409789997, "max": 0.0033820844726385997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256443571428571, "min": 0.10256443571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359020999999998, "min": 1.3886848, "max": 2.5273614000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002661871278571429, "min": 0.0002661871278571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00372661979, "min": 0.00372661979, "max": 0.11276340386, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007945357821881771, "min": 0.007841916754841805, "max": 0.4484417140483856, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11123500764369965, "min": 0.10978683084249496, "max": 3.139091968536377, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 477.59375, "min": 475.01724137931035, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30566.0, "min": 15984.0, "max": 33927.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3348468493204564, "min": -1.0000000521540642, "max": 1.426813539054434, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 85.43019835650921, "min": -30.430601701140404, "max": 85.43019835650921, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3348468493204564, "min": -1.0000000521540642, "max": 1.426813539054434, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 85.43019835650921, "min": -30.430601701140404, "max": 85.43019835650921, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039067012739906204, "min": 0.039067012739906204, "max": 8.548958415165544, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.500288815353997, "min": 2.397054815039155, "max": 136.7833346426487, "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": "1705996204", "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": "1705998479" }, "total": 2274.721648879, "count": 1, "self": 0.5381626190001043, "children": { "run_training.setup": { "total": 0.05734519399993587, "count": 1, "self": 0.05734519399993587 }, "TrainerController.start_learning": { "total": 2274.126141066, "count": 1, "self": 1.6276462009623174, "children": { "TrainerController._reset_env": { "total": 2.192097080000167, "count": 1, "self": 2.192097080000167 }, "TrainerController.advance": { "total": 2270.2121083090374, "count": 63397, "self": 1.7183481460815528, "children": { "env_step": { "total": 1605.251832245003, "count": 63397, "self": 1459.3809980919411, "children": { "SubprocessEnvManager._take_step": { "total": 144.82554407299972, "count": 63397, "self": 5.1369603720204395, "children": { "TorchPolicy.evaluate": { "total": 139.68858370097928, "count": 62555, "self": 139.68858370097928 } } }, "workers": { "total": 1.0452900800621592, "count": 63397, "self": 0.0, "children": { "worker_root": { "total": 2268.2467710479996, "count": 63397, "is_parallel": true, "self": 940.4584088150386, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017831079999268695, "count": 1, "is_parallel": true, "self": 0.000567475000025297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012156329999015725, "count": 8, "is_parallel": true, "self": 0.0012156329999015725 } } }, "UnityEnvironment.step": { "total": 0.05165021299990258, "count": 1, "is_parallel": true, "self": 0.0006595339998511918, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004958330000590649, "count": 1, "is_parallel": true, "self": 0.0004958330000590649 }, "communicator.exchange": { "total": 0.048741466000137734, "count": 1, "is_parallel": true, "self": 0.048741466000137734 }, "steps_from_proto": { "total": 0.0017533799998545874, "count": 1, "is_parallel": true, "self": 0.00036571099985849287, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013876689999960945, "count": 8, "is_parallel": true, "self": 0.0013876689999960945 } } } } } } }, "UnityEnvironment.step": { "total": 1327.788362232961, "count": 63396, "is_parallel": true, "self": 37.67857611488671, "children": { "UnityEnvironment._generate_step_input": { "total": 25.811208891037495, "count": 63396, "is_parallel": true, "self": 25.811208891037495 }, "communicator.exchange": { "total": 1158.189734722021, "count": 63396, "is_parallel": true, "self": 1158.189734722021 }, "steps_from_proto": { "total": 106.10884250501567, "count": 63396, "is_parallel": true, "self": 21.60458592113264, "children": { "_process_rank_one_or_two_observation": { "total": 84.50425658388303, "count": 507168, "is_parallel": true, "self": 84.50425658388303 } } } } } } } } } } }, "trainer_advance": { "total": 663.2419279179528, "count": 63397, "self": 3.065219162866697, "children": { "process_trajectory": { "total": 131.8699640780917, "count": 63397, "self": 131.62843865909167, "children": { "RLTrainer._checkpoint": { "total": 0.2415254190000269, "count": 2, "self": 0.2415254190000269 } } }, "_update_policy": { "total": 528.3067446769944, "count": 445, "self": 314.05041740302977, "children": { "TorchPPOOptimizer.update": { "total": 214.25632727396464, "count": 22761, "self": 214.25632727396464 } } } } } } }, "trainer_threads": { "total": 1.0160001693293452e-06, "count": 1, "self": 1.0160001693293452e-06 }, "TrainerController._save_models": { "total": 0.09428845999991609, "count": 1, "self": 0.001555488999656518, "children": { "RLTrainer._checkpoint": { "total": 0.09273297100025957, "count": 1, "self": 0.09273297100025957 } } } } } } }