{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3658921718597412, "min": 0.3658921718597412, "max": 1.40304434299469, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11064.5791015625, "min": 11010.337890625, "max": 42562.75390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5183396339416504, "min": -0.15780578553676605, "max": 0.5317763686180115, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.02505493164062, "min": -37.39997100830078, "max": 147.83383178710938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012214195914566517, "min": -0.05941685661673546, "max": 0.27046719193458557, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3466897010803223, "min": -15.567216873168945, "max": 64.91212463378906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06719285660628452, "min": 0.06581234171365698, "max": 0.07404424401040477, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9406999924879832, "min": 0.5180034804587446, "max": 1.068481041419242, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01516080430502327, "min": 0.00020752338728321457, "max": 0.017322474211964402, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2122512602703258, "min": 0.0026978040346817894, "max": 0.24251463896750164, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.720254569471425e-06, "min": 7.720254569471425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010808356397259995, "min": 0.00010808356397259995, "max": 0.0035075099308301003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257338571428572, "min": 0.10257338571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360274, "min": 1.3691136000000002, "max": 2.569169900000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026708123285714276, "min": 0.00026708123285714276, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003739137259999999, "min": 0.003739137259999999, "max": 0.11694007300999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009484245441854, "min": 0.009368089027702808, "max": 0.37588930130004883, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13277943432331085, "min": 0.13115324079990387, "max": 2.631225109100342, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 384.78205128205127, "min": 343.6896551724138, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30013.0, "min": 15984.0, "max": 32755.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5126179267580693, "min": -1.0000000521540642, "max": 1.6333195216011727, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.9841982871294, "min": -32.000001668930054, "max": 142.09879837930202, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5126179267580693, "min": -1.0000000521540642, "max": 1.6333195216011727, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.9841982871294, "min": -32.000001668930054, "max": 142.09879837930202, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037869309636731394, "min": 0.03374406400045658, "max": 7.041076235473156, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9538061516650487, "min": 2.766194458527025, "max": 112.6572197675705, "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": "1755847352", "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": "1755849681" }, "total": 2329.17424011, "count": 1, "self": 0.48141681000015524, "children": { "run_training.setup": { "total": 0.022670258999824, "count": 1, "self": 0.022670258999824 }, "TrainerController.start_learning": { "total": 2328.670153041, "count": 1, "self": 1.561426970921275, "children": { "TrainerController._reset_env": { "total": 2.192750083000192, "count": 1, "self": 2.192750083000192 }, "TrainerController.advance": { "total": 2324.840017764079, "count": 63897, "self": 1.5317924219393717, "children": { "env_step": { "total": 1662.9312743510595, "count": 63897, "self": 1504.6757929730834, "children": { "SubprocessEnvManager._take_step": { "total": 157.32366999096894, "count": 63897, "self": 4.747693041944785, "children": { "TorchPolicy.evaluate": { "total": 152.57597694902415, "count": 62561, "self": 152.57597694902415 } } }, "workers": { "total": 0.9318113870072011, "count": 63897, "self": 0.0, "children": { "worker_root": { "total": 2323.2794194439675, "count": 63897, "is_parallel": true, "self": 936.1853796140022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001846195999860356, "count": 1, "is_parallel": true, "self": 0.0006047239999134035, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012414719999469526, "count": 8, "is_parallel": true, "self": 0.0012414719999469526 } } }, "UnityEnvironment.step": { "total": 0.048026519999893935, "count": 1, "is_parallel": true, "self": 0.0005551440003728203, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004822969999622728, "count": 1, "is_parallel": true, "self": 0.0004822969999622728 }, "communicator.exchange": { "total": 0.04534081799965861, "count": 1, "is_parallel": true, "self": 0.04534081799965861 }, "steps_from_proto": { "total": 0.0016482609999002307, "count": 1, "is_parallel": true, "self": 0.0003549359994394763, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012933250004607544, "count": 8, "is_parallel": true, "self": 0.0012933250004607544 } } } } } } }, "UnityEnvironment.step": { "total": 1387.0940398299654, "count": 63896, "is_parallel": true, "self": 32.47351395599344, "children": { "UnityEnvironment._generate_step_input": { "total": 22.34778319104589, "count": 63896, "is_parallel": true, "self": 22.34778319104589 }, "communicator.exchange": { "total": 1235.8133841759504, "count": 63896, "is_parallel": true, "self": 1235.8133841759504 }, "steps_from_proto": { "total": 96.4593585069756, "count": 63896, "is_parallel": true, "self": 19.68551825403256, "children": { "_process_rank_one_or_two_observation": { "total": 76.77384025294305, "count": 511168, "is_parallel": true, "self": 76.77384025294305 } } } } } } } } } } }, "trainer_advance": { "total": 660.3769509910803, "count": 63897, "self": 2.947052429022733, "children": { "process_trajectory": { "total": 124.23151247105943, "count": 63897, "self": 124.03608096905964, "children": { "RLTrainer._checkpoint": { "total": 0.1954315019997921, "count": 2, "self": 0.1954315019997921 } } }, "_update_policy": { "total": 533.1983860909982, "count": 449, "self": 295.40408651901544, "children": { "TorchPPOOptimizer.update": { "total": 237.79429957198272, "count": 22785, "self": 237.79429957198272 } } } } } } }, "trainer_threads": { "total": 7.779999577905983e-07, "count": 1, "self": 7.779999577905983e-07 }, "TrainerController._save_models": { "total": 0.07595744499940338, "count": 1, "self": 0.0010800869995364337, "children": { "RLTrainer._checkpoint": { "total": 0.07487735799986694, "count": 1, "self": 0.07487735799986694 } } } } } } }