{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19976142048835754, "min": 0.19287817180156708, "max": 1.3887903690338135, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5932.115234375, "min": 5772.59130859375, "max": 42130.34375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999938.0, "min": 29952.0, "max": 2999938.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999938.0, "min": 29952.0, "max": 2999938.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7580035328865051, "min": -0.11930020898580551, "max": 0.8287280797958374, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 224.36904907226562, "min": -28.870651245117188, "max": 250.60165405273438, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.002562984125688672, "min": -0.035717565566301346, "max": 0.452360600233078, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.7586432695388794, "min": -9.929483413696289, "max": 107.20946502685547, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06513366848576836, "min": 0.06357793817375158, "max": 0.07285739216396385, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9118713588007571, "min": 0.49459544458308113, "max": 1.0899526003437738, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015255500468941006, "min": 8.76807708519699e-05, "max": 0.01588612093335195, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2135770065651741, "min": 0.0011398500210756087, "max": 0.22920441717724316, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5547851960571466e-06, "min": 1.5547851960571466e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1766992744800053e-05, "min": 2.1766992744800053e-05, "max": 0.0039274443908519, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051822857142857, "min": 0.10051822857142857, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4072552, "min": 1.3897045333333333, "max": 2.7375185333333336, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.17710342857144e-05, "min": 6.17710342857144e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008647944800000018, "min": 0.0008647944800000018, "max": 0.13092389519, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005368842743337154, "min": 0.005081643350422382, "max": 0.5240278840065002, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07516379654407501, "min": 0.0711430087685585, "max": 3.6681952476501465, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 255.2377049180328, "min": 224.8984375, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31139.0, "min": 15984.0, "max": 32691.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.71196720052938, "min": -1.0000000521540642, "max": 1.767444428706926, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 208.85999846458435, "min": -32.000001668930054, "max": 229.1545986533165, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.71196720052938, "min": -1.0000000521540642, "max": 1.767444428706926, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 208.85999846458435, "min": -32.000001668930054, "max": 229.1545986533165, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014275661010899176, "min": 0.012101938975831672, "max": 12.159518081694841, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7416306433296995, "min": 1.549048188906454, "max": 194.55228930711746, "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": "1751656233", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751667319" }, "total": 11085.767648921, "count": 1, "self": 0.9516570060004597, "children": { "run_training.setup": { "total": 0.02689954699997088, "count": 1, "self": 0.02689954699997088 }, "TrainerController.start_learning": { "total": 11084.789092368, "count": 1, "self": 7.870291435010586, "children": { "TrainerController._reset_env": { "total": 4.185366544000033, "count": 1, "self": 4.185366544000033 }, "TrainerController.advance": { "total": 11072.64170806699, "count": 194865, "self": 8.337693987437888, "children": { "env_step": { "total": 7773.339780542464, "count": 194865, "self": 7253.387262097363, "children": { "SubprocessEnvManager._take_step": { "total": 515.2595091569448, "count": 194865, "self": 23.302590708153275, "children": { "TorchPolicy.evaluate": { "total": 491.9569184487915, "count": 187551, "self": 491.9569184487915 } } }, "workers": { "total": 4.693009288156077, "count": 194865, "self": 0.0, "children": { "worker_root": { "total": 11054.970103040081, "count": 194865, "is_parallel": true, "self": 4398.237728479163, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00694653099998277, "count": 1, "is_parallel": true, "self": 0.00522465199992439, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017218790000583795, "count": 8, "is_parallel": true, "self": 0.0017218790000583795 } } }, "UnityEnvironment.step": { "total": 0.11371382499999072, "count": 1, "is_parallel": true, "self": 0.0007157710000456063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005893489999948542, "count": 1, "is_parallel": true, "self": 0.0005893489999948542 }, "communicator.exchange": { "total": 0.11033493699994779, "count": 1, "is_parallel": true, "self": 0.11033493699994779 }, "steps_from_proto": { "total": 0.002073768000002474, "count": 1, "is_parallel": true, "self": 0.00047826899987057914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015954990001318947, "count": 8, "is_parallel": true, "self": 0.0015954990001318947 } } } } } } }, "UnityEnvironment.step": { "total": 6656.732374560918, "count": 194864, "is_parallel": true, "self": 143.94942956041177, "children": { "UnityEnvironment._generate_step_input": { "total": 96.83458658111175, "count": 194864, "is_parallel": true, "self": 96.83458658111175 }, "communicator.exchange": { "total": 6016.209713463404, "count": 194864, "is_parallel": true, "self": 6016.209713463404 }, "steps_from_proto": { "total": 399.7386449559905, "count": 194864, "is_parallel": true, "self": 89.12424320833253, "children": { "_process_rank_one_or_two_observation": { "total": 310.61440174765795, "count": 1558912, "is_parallel": true, "self": 310.61440174765795 } } } } } } } } } } }, "trainer_advance": { "total": 3290.9642335370895, "count": 194865, "self": 16.5348104640334, "children": { "process_trajectory": { "total": 525.746761769063, "count": 194865, "self": 524.7441291050615, "children": { "RLTrainer._checkpoint": { "total": 1.0026326640015668, "count": 6, "self": 1.0026326640015668 } } }, "_update_policy": { "total": 2748.682661303993, "count": 1383, "self": 1081.1511972020428, "children": { "TorchPPOOptimizer.update": { "total": 1667.5314641019502, "count": 68391, "self": 1667.5314641019502 } } } } } } }, "trainer_threads": { "total": 1.1110005289083347e-06, "count": 1, "self": 1.1110005289083347e-06 }, "TrainerController._save_models": { "total": 0.09172521099935693, "count": 1, "self": 0.002658923998751561, "children": { "RLTrainer._checkpoint": { "total": 0.08906628700060537, "count": 1, "self": 0.08906628700060537 } } } } } } }