{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13997095823287964, "min": 0.13515740633010864, "max": 1.5335098505020142, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4185.69140625, "min": 4050.397216796875, "max": 46520.5546875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999951.0, "min": 29974.0, "max": 2999951.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999951.0, "min": 29974.0, "max": 2999951.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8112826347351074, "min": -0.10546746850013733, "max": 0.8812189102172852, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 245.81863403320312, "min": -25.417659759521484, "max": 273.1778564453125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013699229806661606, "min": -0.005644344259053469, "max": 0.1852613240480423, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.150866508483887, "min": -1.66508150100708, "max": 44.647979736328125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07026074094063092, "min": 0.06211566593746149, "max": 0.07511671141892497, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.983650373168833, "min": 0.5947844996523509, "max": 1.121613116217001, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015531344338640094, "min": 0.0005532349624091268, "max": 0.01795476450795485, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21743882074096132, "min": 0.007192054511318649, "max": 0.2513667031113679, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4412923767452392e-06, "min": 1.4412923767452392e-06, "max": 0.00029828397557200837, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.017809327443335e-05, "min": 2.017809327443335e-05, "max": 0.004010949563016833, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004803976190476, "min": 0.1004803976190476, "max": 0.19942799166666667, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067255666666665, "min": 1.4067255666666665, "max": 2.7975145666666674, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.799172214285719e-05, "min": 5.799172214285719e-05, "max": 0.009942856367499999, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008118841100000007, "min": 0.0008118841100000007, "max": 0.13370461835, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005496342666447163, "min": 0.005496342666447163, "max": 0.3608822226524353, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07694879919290543, "min": 0.07694879919290543, "max": 2.8870577812194824, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 231.5859375, "min": 202.80141843971631, "max": 995.53125, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29643.0, "min": 16261.0, "max": 33373.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7212968617677689, "min": -0.9337813011370599, "max": 1.7942777725143566, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 220.3259983062744, "min": -29.881001636385918, "max": 268.265997633338, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7212968617677689, "min": -0.9337813011370599, "max": 1.7942777725143566, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 220.3259983062744, "min": -29.881001636385918, "max": 268.265997633338, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013274244590974149, "min": 0.012789758633581116, "max": 7.566931799054146, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.699103307644691, "min": 1.699103307644691, "max": 128.63784058392048, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1743247210", "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": "1743254608" }, "total": 7398.44707014, "count": 1, "self": 0.5312970799986942, "children": { "run_training.setup": { "total": 0.019611703000009584, "count": 1, "self": 0.019611703000009584 }, "TrainerController.start_learning": { "total": 7397.896161357001, "count": 1, "self": 4.140634342924386, "children": { "TrainerController._reset_env": { "total": 2.100141836000148, "count": 1, "self": 2.100141836000148 }, "TrainerController.advance": { "total": 7391.564862175074, "count": 195415, "self": 4.192528928921092, "children": { "env_step": { "total": 5349.433735135832, "count": 195415, "self": 4883.7247261575485, "children": { "SubprocessEnvManager._take_step": { "total": 463.29011357131367, "count": 195415, "self": 13.96375521139953, "children": { "TorchPolicy.evaluate": { "total": 449.32635835991414, "count": 187555, "self": 449.32635835991414 } } }, "workers": { "total": 2.4188954069691135, "count": 195415, "self": 0.0, "children": { "worker_root": { "total": 7382.397145986948, "count": 195415, "is_parallel": true, "self": 2843.0253636796224, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021031010001024697, "count": 1, "is_parallel": true, "self": 0.0006904639999447681, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014126370001577016, "count": 8, "is_parallel": true, "self": 0.0014126370001577016 } } }, "UnityEnvironment.step": { "total": 0.04908028700037903, "count": 1, "is_parallel": true, "self": 0.0005147440001564973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004972369997631176, "count": 1, "is_parallel": true, "self": 0.0004972369997631176 }, "communicator.exchange": { "total": 0.04638279300024806, "count": 1, "is_parallel": true, "self": 0.04638279300024806 }, "steps_from_proto": { "total": 0.0016855130002113583, "count": 1, "is_parallel": true, "self": 0.00035757500108957174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013279379991217866, "count": 8, "is_parallel": true, "self": 0.0013279379991217866 } } } } } } }, "UnityEnvironment.step": { "total": 4539.371782307326, "count": 195414, "is_parallel": true, "self": 95.84744425767713, "children": { "UnityEnvironment._generate_step_input": { "total": 70.715368155139, "count": 195414, "is_parallel": true, "self": 70.715368155139 }, "communicator.exchange": { "total": 4080.673982500776, "count": 195414, "is_parallel": true, "self": 4080.673982500776 }, "steps_from_proto": { "total": 292.13498739373335, "count": 195414, "is_parallel": true, "self": 59.96355395639603, "children": { "_process_rank_one_or_two_observation": { "total": 232.17143343733733, "count": 1563312, "is_parallel": true, "self": 232.17143343733733 } } } } } } } } } } }, "trainer_advance": { "total": 2037.9385981103214, "count": 195415, "self": 8.572907293308617, "children": { "process_trajectory": { "total": 395.5845103520005, "count": 195415, "self": 394.9405266760009, "children": { "RLTrainer._checkpoint": { "total": 0.6439836759996069, "count": 6, "self": 0.6439836759996069 } } }, "_update_policy": { "total": 1633.7811804650123, "count": 1401, "self": 891.1595728188636, "children": { "TorchPPOOptimizer.update": { "total": 742.6216076461487, "count": 68421, "self": 742.6216076461487 } } } } } } }, "trainer_threads": { "total": 8.750012057134882e-07, "count": 1, "self": 8.750012057134882e-07 }, "TrainerController._save_models": { "total": 0.09052212800088455, "count": 1, "self": 0.001743404001899762, "children": { "RLTrainer._checkpoint": { "total": 0.08877872399898479, "count": 1, "self": 0.08877872399898479 } } } } } } }