{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13689710199832916, "min": 0.1177377700805664, "max": 1.4125113487243652, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4100.341796875, "min": 3518.946533203125, "max": 42849.9453125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999985.0, "min": 29987.0, "max": 2999985.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999985.0, "min": 29987.0, "max": 2999985.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.871915340423584, "min": -0.08985260128974915, "max": 0.9122087955474854, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 271.1656799316406, "min": -21.564624786376953, "max": 280.048095703125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018306860700249672, "min": -0.01786121539771557, "max": 0.7513640522956848, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.69343376159668, "min": -4.87611198425293, "max": 178.82464599609375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06929773124854774, "min": 0.06350942469102197, "max": 0.07448223320711993, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9701682374796684, "min": 0.5835752889020469, "max": 1.0866661710703434, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014570308731455052, "min": 0.0009128543780996247, "max": 0.026121248675566467, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20398432224037072, "min": 0.011867106915295121, "max": 0.25310028748936014, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5028137848095236e-06, "min": 1.5028137848095236e-06, "max": 0.0002984077130307625, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1039392987333332e-05, "min": 2.1039392987333332e-05, "max": 0.004010802063066, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050090476190476, "min": 0.10050090476190476, "max": 0.1994692375, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070126666666667, "min": 1.4070126666666667, "max": 2.827554933333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0040385714285714e-05, "min": 6.0040385714285714e-05, "max": 0.00994697682625, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008405654, "min": 0.0008405654, "max": 0.1336997066, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008786150254309177, "min": 0.008670860901474953, "max": 0.7231569290161133, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12300609797239304, "min": 0.12139205634593964, "max": 5.785255432128906, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 196.88888888888889, "min": 192.7516339869281, "max": 997.6875, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30124.0, "min": 15891.0, "max": 32976.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.803111099729351, "min": -0.935956300701946, "max": 1.805784302696683, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 275.8759982585907, "min": -29.950601622462273, "max": 276.2849983125925, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.803111099729351, "min": -0.935956300701946, "max": 1.805784302696683, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 275.8759982585907, "min": -29.950601622462273, "max": 276.2849983125925, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01800723419466902, "min": 0.01800723419466902, "max": 17.034468912519515, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.75510683178436, "min": 2.567502475998481, "max": 272.55150260031223, "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": "1773754754", "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 --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": "1773762131" }, "total": 7377.181409056, "count": 1, "self": 0.9136139219990582, "children": { "run_training.setup": { "total": 0.03346269100029531, "count": 1, "self": 0.03346269100029531 }, "TrainerController.start_learning": { "total": 7376.234332443, "count": 1, "self": 4.411734970826728, "children": { "TrainerController._reset_env": { "total": 3.3494539970001824, "count": 1, "self": 3.3494539970001824 }, "TrainerController.advance": { "total": 7368.355997679172, "count": 195748, "self": 4.338809334260986, "children": { "env_step": { "total": 5374.1125881290245, "count": 195748, "self": 4916.786620469571, "children": { "SubprocessEnvManager._take_step": { "total": 454.7656540121793, "count": 195748, "self": 14.076715744915418, "children": { "TorchPolicy.evaluate": { "total": 440.6889382672639, "count": 187555, "self": 440.6889382672639 } } }, "workers": { "total": 2.560313647273688, "count": 195748, "self": 0.0, "children": { "worker_root": { "total": 7356.593362077077, "count": 195748, "is_parallel": true, "self": 2795.657948138044, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004086649999862857, "count": 1, "is_parallel": true, "self": 0.002756465000402386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013301849994604709, "count": 8, "is_parallel": true, "self": 0.0013301849994604709 } } }, "UnityEnvironment.step": { "total": 0.050104006999845296, "count": 1, "is_parallel": true, "self": 0.0005435799998849689, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004720000001725566, "count": 1, "is_parallel": true, "self": 0.0004720000001725566 }, "communicator.exchange": { "total": 0.04737354200005939, "count": 1, "is_parallel": true, "self": 0.04737354200005939 }, "steps_from_proto": { "total": 0.0017148849997283833, "count": 1, "is_parallel": true, "self": 0.0003799290007009404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013349559990274429, "count": 8, "is_parallel": true, "self": 0.0013349559990274429 } } } } } } }, "UnityEnvironment.step": { "total": 4560.9354139390325, "count": 195747, "is_parallel": true, "self": 103.36898465292325, "children": { "UnityEnvironment._generate_step_input": { "total": 69.48728274718678, "count": 195747, "is_parallel": true, "self": 69.48728274718678 }, "communicator.exchange": { "total": 4064.4594844567846, "count": 195747, "is_parallel": true, "self": 4064.4594844567846 }, "steps_from_proto": { "total": 323.61966208213744, "count": 195747, "is_parallel": true, "self": 68.88087494683668, "children": { "_process_rank_one_or_two_observation": { "total": 254.73878713530075, "count": 1565976, "is_parallel": true, "self": 254.73878713530075 } } } } } } } } } } }, "trainer_advance": { "total": 1989.9046002158861, "count": 195748, "self": 8.633077081159172, "children": { "process_trajectory": { "total": 392.7209531667422, "count": 195748, "self": 392.09866482074176, "children": { "RLTrainer._checkpoint": { "total": 0.6222883460004596, "count": 6, "self": 0.6222883460004596 } } }, "_update_policy": { "total": 1588.5505699679848, "count": 1406, "self": 868.9630616727623, "children": { "TorchPPOOptimizer.update": { "total": 719.5875082952225, "count": 68397, "self": 719.5875082952225 } } } } } } }, "trainer_threads": { "total": 1.1860010999953374e-06, "count": 1, "self": 1.1860010999953374e-06 }, "TrainerController._save_models": { "total": 0.11714460999974108, "count": 1, "self": 0.0015571159983664984, "children": { "RLTrainer._checkpoint": { "total": 0.11558749400137458, "count": 1, "self": 0.11558749400137458 } } } } } } }