{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19739755988121033, "min": 0.18612922728061676, "max": 1.448979377746582, "count": 70 }, "Pyramids.Policy.Entropy.sum": { "value": 5899.818359375, "min": 5568.986328125, "max": 43956.23828125, "count": 70 }, "Pyramids.Step.mean": { "value": 2099889.0, "min": 29952.0, "max": 2099889.0, "count": 70 }, "Pyramids.Step.sum": { "value": 2099889.0, "min": 29952.0, "max": 2099889.0, "count": 70 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8246093988418579, "min": -0.1120196133852005, "max": 0.8246093988418579, "count": 70 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 250.68125915527344, "min": -27.108745574951172, "max": 250.68125915527344, "count": 70 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012902140617370605, "min": -0.005089040379971266, "max": 0.29539987444877625, "count": 70 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.922250747680664, "min": -1.3231505155563354, "max": 70.8959732055664, "count": 70 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07084840858199945, "min": 0.06379275239590902, "max": 0.07337246633029455, "count": 70 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9918777201479922, "min": 0.49806185708389267, "max": 1.06551817581788, "count": 70 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014129798516348404, "min": 0.000255498857455707, "max": 0.01666433808806176, "count": 70 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19781717922887765, "min": 0.00255498857455707, "max": 0.2499650713209264, "count": 70 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.154092662923807e-05, "min": 9.154092662923807e-05, "max": 0.00029838354339596195, "count": 70 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.001281572972809333, "min": 0.001281572972809333, "max": 0.003927392890869066, "count": 70 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13051361904761907, "min": 0.13051361904761907, "max": 0.19946118095238097, "count": 70 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8271906666666669, "min": 1.3897045333333333, "max": 2.7525863000000004, "count": 70 }, "Pyramids.Policy.Beta.mean": { "value": 0.0030583105428571428, "min": 0.0030583105428571428, "max": 0.009946171977142856, "count": 70 }, "Pyramids.Policy.Beta.sum": { "value": 0.0428163476, "min": 0.0428163476, "max": 0.13092218024, "count": 70 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007405238691717386, "min": 0.007195088546723127, "max": 0.4440057575702667, "count": 70 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10367333889007568, "min": 0.10073123872280121, "max": 3.1080403327941895, "count": 70 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 223.86153846153846, "min": 223.86153846153846, "max": 999.0, "count": 70 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29102.0, "min": 15984.0, "max": 32527.0, "count": 70 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7760915912062156, "min": -1.0000000521540642, "max": 1.7760915912062156, "count": 70 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 232.66799844801426, "min": -32.000001668930054, "max": 232.66799844801426, "count": 70 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7760915912062156, "min": -1.0000000521540642, "max": 1.7760915912062156, "count": 70 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 232.66799844801426, "min": -32.000001668930054, "max": 232.66799844801426, "count": 70 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017356182540098616, "min": 0.017356182540098616, "max": 9.865679629147053, "count": 70 }, "Pyramids.Policy.RndReward.sum": { "value": 2.273659912752919, "min": 2.208571456845675, "max": 157.85087406635284, "count": 70 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 70 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 70 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1778408168", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1778413697" }, "total": 5528.7845643969995, "count": 1, "self": 0.4809384089985542, "children": { "run_training.setup": { "total": 0.023013235000235, "count": 1, "self": 0.023013235000235 }, "TrainerController.start_learning": { "total": 5528.280612753, "count": 1, "self": 3.1032701481281038, "children": { "TrainerController._reset_env": { "total": 2.439205122000203, "count": 1, "self": 2.439205122000203 }, "TrainerController.advance": { "total": 5522.735801486871, "count": 135811, "self": 3.1467679639372363, "children": { "env_step": { "total": 4091.047542019864, "count": 135811, "self": 3758.9009577827283, "children": { "SubprocessEnvManager._take_step": { "total": 330.3256099940645, "count": 135811, "self": 10.129508271056238, "children": { "TorchPolicy.evaluate": { "total": 320.19610172300827, "count": 131453, "self": 320.19610172300827 } } }, "workers": { "total": 1.820974243071305, "count": 135810, "self": 0.0, "children": { "worker_root": { "total": 5516.567680162971, "count": 135810, "is_parallel": true, "self": 2014.0170179329953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018933159999505733, "count": 1, "is_parallel": true, "self": 0.0006829849994574033, "children": { "_process_rank_one_or_two_observation": { "total": 0.00121033100049317, "count": 8, "is_parallel": true, "self": 0.00121033100049317 } } }, "UnityEnvironment.step": { "total": 0.11307460199986963, "count": 1, "is_parallel": true, "self": 0.000638511000033759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004447540000001027, "count": 1, "is_parallel": true, "self": 0.0004447540000001027 }, "communicator.exchange": { "total": 0.10818671799961521, "count": 1, "is_parallel": true, "self": 0.10818671799961521 }, "steps_from_proto": { "total": 0.003804619000220555, "count": 1, "is_parallel": true, "self": 0.00038620599980276893, "children": { "_process_rank_one_or_two_observation": { "total": 0.003418413000417786, "count": 8, "is_parallel": true, "self": 0.003418413000417786 } } } } } } }, "UnityEnvironment.step": { "total": 3502.5506622299754, "count": 135809, "is_parallel": true, "self": 73.41311380630032, "children": { "UnityEnvironment._generate_step_input": { "total": 51.656995305956116, "count": 135809, "is_parallel": true, "self": 51.656995305956116 }, "communicator.exchange": { "total": 3138.137845860854, "count": 135809, "is_parallel": true, "self": 3138.137845860854 }, "steps_from_proto": { "total": 239.34270725686474, "count": 135809, "is_parallel": true, "self": 49.29209056050286, "children": { "_process_rank_one_or_two_observation": { "total": 190.05061669636189, "count": 1086472, "is_parallel": true, "self": 190.05061669636189 } } } } } } } } } } }, "trainer_advance": { "total": 1428.5414915030701, "count": 135810, "self": 6.0324705011607875, "children": { "process_trajectory": { "total": 276.25981750492156, "count": 135810, "self": 275.8598004929222, "children": { "RLTrainer._checkpoint": { "total": 0.4000170119993527, "count": 4, "self": 0.4000170119993527 } } }, "_update_policy": { "total": 1146.2492034969878, "count": 963, "self": 627.9275552599656, "children": { "TorchPPOOptimizer.update": { "total": 518.3216482370221, "count": 47919, "self": 518.3216482370221 } } } } } } }, "trainer_threads": { "total": 1.3079998097964562e-06, "count": 1, "self": 1.3079998097964562e-06 }, "TrainerController._save_models": { "total": 0.002334688000701135, "count": 1, "self": 2.506200053176144e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0023096260001693736, "count": 1, "self": 0.0023096260001693736 } } } } } } }