{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7448220252990723, "min": 0.7285001277923584, "max": 1.517684817314148, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22380.412109375, "min": 21759.201171875, "max": 46040.48828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2869012653827667, "min": -0.10125422477722168, "max": 0.2869012653827667, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 73.15982055664062, "min": -24.301013946533203, "max": 73.15982055664062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07460573315620422, "min": -0.02357194945216179, "max": 0.17345908284187317, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 19.02446174621582, "min": -5.987275123596191, "max": 41.63018035888672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07139145691177341, "min": 0.06448559831664506, "max": 0.07314192422783027, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9994803967648277, "min": 0.49657393146263457, "max": 1.0739827966671347, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012505578871198289, "min": 5.7939525677462445e-05, "max": 0.012906822378821797, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17507810419677605, "min": 0.0008111533594844742, "max": 0.18069551330350517, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.359397546900002e-06, "min": 7.359397546900002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010303156565660002, "min": 0.00010303156565660002, "max": 0.0035077913307363, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245309999999999, "min": 0.10245309999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343434, "min": 1.3691136000000002, "max": 2.5692637, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025506469000000006, "min": 0.00025506469000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003570905660000001, "min": 0.003570905660000001, "max": 0.11694944363000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010814101435244083, "min": 0.010814101435244083, "max": 0.32483014464378357, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15139742195606232, "min": 0.15139742195606232, "max": 2.273811101913452, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 577.56, "min": 537.1206896551724, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28878.0, "min": 15984.0, "max": 32921.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.022295972406864, "min": -1.0000000521540642, "max": 1.255917211673383, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 51.11479862034321, "min": -32.000001668930054, "max": 72.84319827705622, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.022295972406864, "min": -1.0000000521540642, "max": 1.255917211673383, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 51.11479862034321, "min": -32.000001668930054, "max": 72.84319827705622, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06501978911168407, "min": 0.06294771162182425, "max": 6.655797706916928, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.250989455584204, "min": 3.250989455584204, "max": 106.49276331067085, "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": "1740055673", "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": "1740057926" }, "total": 2253.4550553910003, "count": 1, "self": 0.5767080430000533, "children": { "run_training.setup": { "total": 0.024090635999982624, "count": 1, "self": 0.024090635999982624 }, "TrainerController.start_learning": { "total": 2252.8542567120003, "count": 1, "self": 1.5792767720540724, "children": { "TrainerController._reset_env": { "total": 2.215807681000115, "count": 1, "self": 2.215807681000115 }, "TrainerController.advance": { "total": 2248.9654714349463, "count": 63329, "self": 1.5896894849674936, "children": { "env_step": { "total": 1553.667692709959, "count": 63329, "self": 1382.184583266971, "children": { "SubprocessEnvManager._take_step": { "total": 170.5783961529412, "count": 63329, "self": 5.0504912878982395, "children": { "TorchPolicy.evaluate": { "total": 165.52790486504296, "count": 62551, "self": 165.52790486504296 } } }, "workers": { "total": 0.9047132900468569, "count": 63329, "self": 0.0, "children": { "worker_root": { "total": 2247.0314005250066, "count": 63329, "is_parallel": true, "self": 987.5733478270295, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002669823000132965, "count": 1, "is_parallel": true, "self": 0.0009627449999243254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017070780002086394, "count": 8, "is_parallel": true, "self": 0.0017070780002086394 } } }, "UnityEnvironment.step": { "total": 0.049093162999952256, "count": 1, "is_parallel": true, "self": 0.0005527280000023893, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004589650000070833, "count": 1, "is_parallel": true, "self": 0.0004589650000070833 }, "communicator.exchange": { "total": 0.04629354799999419, "count": 1, "is_parallel": true, "self": 0.04629354799999419 }, "steps_from_proto": { "total": 0.001787921999948594, "count": 1, "is_parallel": true, "self": 0.0003774730000714044, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014104489998771896, "count": 8, "is_parallel": true, "self": 0.0014104489998771896 } } } } } } }, "UnityEnvironment.step": { "total": 1259.458052697977, "count": 63328, "is_parallel": true, "self": 33.37086270199438, "children": { "UnityEnvironment._generate_step_input": { "total": 24.274842388984553, "count": 63328, "is_parallel": true, "self": 24.274842388984553 }, "communicator.exchange": { "total": 1100.2576939179953, "count": 63328, "is_parallel": true, "self": 1100.2576939179953 }, "steps_from_proto": { "total": 101.55465368900286, "count": 63328, "is_parallel": true, "self": 21.02511819775077, "children": { "_process_rank_one_or_two_observation": { "total": 80.52953549125209, "count": 506624, "is_parallel": true, "self": 80.52953549125209 } } } } } } } } } } }, "trainer_advance": { "total": 693.7080892400197, "count": 63329, "self": 2.956233343065378, "children": { "process_trajectory": { "total": 131.99612444395257, "count": 63329, "self": 131.7814221969527, "children": { "RLTrainer._checkpoint": { "total": 0.2147022469998774, "count": 2, "self": 0.2147022469998774 } } }, "_update_policy": { "total": 558.7557314530018, "count": 445, "self": 306.18615769601183, "children": { "TorchPPOOptimizer.update": { "total": 252.56957375698994, "count": 22761, "self": 252.56957375698994 } } } } } } }, "trainer_threads": { "total": 9.57999873207882e-07, "count": 1, "self": 9.57999873207882e-07 }, "TrainerController._save_models": { "total": 0.09369986599995173, "count": 1, "self": 0.0012924860002385685, "children": { "RLTrainer._checkpoint": { "total": 0.09240737999971316, "count": 1, "self": 0.09240737999971316 } } } } } } }