{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27496418356895447, "min": 0.2618868052959442, "max": 1.4444835186004639, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8244.5263671875, "min": 7844.033203125, "max": 43819.8515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989874.0, "min": 29922.0, "max": 989874.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989874.0, "min": 29922.0, "max": 989874.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.716020405292511, "min": -0.06699221581220627, "max": 0.7693420648574829, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 208.3619384765625, "min": -16.1989803314209, "max": 223.8785400390625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03290698304772377, "min": -0.008291473612189293, "max": 0.34210288524627686, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.575931549072266, "min": -2.396235942840576, "max": 82.10469055175781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06912151260864145, "min": 0.06528382221655367, "max": 0.0722951659077283, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0368226891296217, "min": 0.5533051696093336, "max": 1.0733261869124058, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015572128542569568, "min": 0.0009247043281447282, "max": 0.016957163061326726, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23358192813854353, "min": 0.009247043281447282, "max": 0.24791281939171458, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.566637477820002e-06, "min": 7.566637477820002e-06, "max": 0.000294843376718875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011349956216730002, "min": 0.00011349956216730002, "max": 0.0036355129881623996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252218, "min": 0.10252218, "max": 0.198281125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378327, "min": 1.4780226000000003, "max": 2.6118376, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002619657820000001, "min": 0.0002619657820000001, "max": 0.0098282843875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003929486730000002, "min": 0.003929486730000002, "max": 0.12120257624, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015109622851014137, "min": 0.014701508916914463, "max": 0.5286263227462769, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2266443371772766, "min": 0.20582112669944763, "max": 4.229010581970215, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 255.3913043478261, "min": 255.00884955752213, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29370.0, "min": 16465.0, "max": 33721.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7272086757032767, "min": -1.0000000521540642, "max": 1.7459017719541277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 198.62899770587683, "min": -32.000001668930054, "max": 206.35779824107885, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7272086757032767, "min": -1.0000000521540642, "max": 1.7459017719541277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 198.62899770587683, "min": -32.000001668930054, "max": 206.35779824107885, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04018895485104345, "min": 0.04018895485104345, "max": 10.721638479653526, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.621729807869997, "min": 4.621729807869997, "max": 182.26785415410995, "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": "1785751211", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda/envs/myenv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids2 --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.13.0+cu130", "numpy_version": "1.23.5", "end_time_seconds": "1785753784" }, "total": 2573.0238469259994, "count": 1, "self": 0.6391100249993542, "children": { "run_training.setup": { "total": 0.02890606800065143, "count": 1, "self": 0.02890606800065143 }, "TrainerController.start_learning": { "total": 2572.3558308329993, "count": 1, "self": 2.075068800945701, "children": { "TrainerController._reset_env": { "total": 4.007465413999853, "count": 1, "self": 4.007465413999853 }, "TrainerController.advance": { "total": 2565.0037811790544, "count": 64484, "self": 1.9953668720436326, "children": { "env_step": { "total": 1831.3928019630039, "count": 64484, "self": 1703.6794269562106, "children": { "SubprocessEnvManager._take_step": { "total": 126.40924987001472, "count": 64484, "self": 4.8320985110185575, "children": { "TorchPolicy.evaluate": { "total": 121.57715135899616, "count": 62557, "self": 121.57715135899616 } } }, "workers": { "total": 1.3041251367785662, "count": 64484, "self": 0.0, "children": { "worker_root": { "total": 2563.9310794498833, "count": 64484, "is_parallel": true, "self": 1002.2425070557892, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024547499997424893, "count": 1, "is_parallel": true, "self": 0.0008595099998274236, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015952399999150657, "count": 8, "is_parallel": true, "self": 0.0015952399999150657 } } }, "UnityEnvironment.step": { "total": 0.06486596600007033, "count": 1, "is_parallel": true, "self": 0.0005783500000688946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046409999958996195, "count": 1, "is_parallel": true, "self": 0.00046409999958996195 }, "communicator.exchange": { "total": 0.062146926000423264, "count": 1, "is_parallel": true, "self": 0.062146926000423264 }, "steps_from_proto": { "total": 0.0016765899999882095, "count": 1, "is_parallel": true, "self": 0.0003470700012258021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013295199987624073, "count": 8, "is_parallel": true, "self": 0.0013295199987624073 } } } } } } }, "UnityEnvironment.step": { "total": 1561.688572394094, "count": 64483, "is_parallel": true, "self": 36.73688697416219, "children": { "UnityEnvironment._generate_step_input": { "total": 25.625829706012155, "count": 64483, "is_parallel": true, "self": 25.625829706012155 }, "communicator.exchange": { "total": 1394.0989183189495, "count": 64483, "is_parallel": true, "self": 1394.0989183189495 }, "steps_from_proto": { "total": 105.22693739497026, "count": 64483, "is_parallel": true, "self": 23.104230682892194, "children": { "_process_rank_one_or_two_observation": { "total": 82.12270671207807, "count": 515864, "is_parallel": true, "self": 82.12270671207807 } } } } } } } } } } }, "trainer_advance": { "total": 731.6156123440069, "count": 64484, "self": 4.053427216121236, "children": { "process_trajectory": { "total": 129.55844717188756, "count": 64484, "self": 124.02484170188745, "children": { "RLTrainer._checkpoint": { "total": 5.533605470000111, "count": 2, "self": 5.533605470000111 } } }, "_update_policy": { "total": 598.0037379559981, "count": 457, "self": 243.50314794098722, "children": { "TorchPPOOptimizer.update": { "total": 354.50059001501086, "count": 22779, "self": 354.50059001501086 } } } } } } }, "trainer_threads": { "total": 9.199993655784056e-07, "count": 1, "self": 9.199993655784056e-07 }, "TrainerController._save_models": { "total": 1.2695145190000403, "count": 1, "self": 0.0005462500002977322, "children": { "RLTrainer._checkpoint": { "total": 1.2689682689997426, "count": 1, "self": 1.2689682689997426 } } } } } } }