{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6812433004379272, "min": 0.6602791547775269, "max": 1.469261884689331, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20535.3984375, "min": 19660.47265625, "max": 44571.52734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3841245770454407, "min": -0.11417458206415176, "max": 0.4420349597930908, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.17713928222656, "min": -27.401899337768555, "max": 118.84973907470703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02561379224061966, "min": -0.014273285865783691, "max": 0.2762005925178528, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.813268661499023, "min": -3.8395137786865234, "max": 66.28813934326172, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07063742418088187, "min": 0.06455440956159707, "max": 0.07398282317962084, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9889239385323462, "min": 0.4787959187671585, "max": 1.1097423476943125, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014744875908701115, "min": 0.0005941775325374848, "max": 0.014744875908701115, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2064282627218156, "min": 0.007282525358643668, "max": 0.21190664000945011, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.374590398978575e-06, "min": 7.374590398978575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010324426558570006, "min": 0.00010324426558570006, "max": 0.0035069948310018006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024581642857143, "min": 0.1024581642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344143000000003, "min": 1.3691136000000002, "max": 2.5689982000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002555706121428573, "min": 0.0002555706121428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035779885700000023, "min": 0.0035779885700000023, "max": 0.11692292017999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007994979619979858, "min": 0.007994979619979858, "max": 0.4559877812862396, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11192971467971802, "min": 0.11192971467971802, "max": 3.1919145584106445, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 455.9384615384615, "min": 401.2857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29636.0, "min": 15984.0, "max": 33909.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3901784416574698, "min": -1.0000000521540642, "max": 1.4583013831099993, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.36159870773554, "min": -32.000001668930054, "max": 111.09839866310358, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3901784416574698, "min": -1.0000000521540642, "max": 1.4583013831099993, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.36159870773554, "min": -32.000001668930054, "max": 111.09839866310358, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03846673479106707, "min": 0.03622929726909308, "max": 8.778084844350815, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5003377614193596, "min": 2.5003377614193596, "max": 140.44935750961304, "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": "1722278956", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722281080" }, "total": 2124.3028889419998, "count": 1, "self": 0.5760231379999823, "children": { "run_training.setup": { "total": 0.053964495999935025, "count": 1, "self": 0.053964495999935025 }, "TrainerController.start_learning": { "total": 2123.672901308, "count": 1, "self": 1.4615707219381875, "children": { "TrainerController._reset_env": { "total": 2.2350833039999998, "count": 1, "self": 2.2350833039999998 }, "TrainerController.advance": { "total": 2119.889193900062, "count": 63515, "self": 1.5171943761001785, "children": { "env_step": { "total": 1474.7694955309698, "count": 63515, "self": 1338.812684422005, "children": { "SubprocessEnvManager._take_step": { "total": 135.046465804945, "count": 63515, "self": 4.818058315967846, "children": { "TorchPolicy.evaluate": { "total": 130.22840748897715, "count": 62547, "self": 130.22840748897715 } } }, "workers": { "total": 0.9103453040197564, "count": 63515, "self": 0.0, "children": { "worker_root": { "total": 2118.4891182390797, "count": 63515, "is_parallel": true, "self": 903.6323602400075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021675309999409365, "count": 1, "is_parallel": true, "self": 0.0006680160004179925, "children": { "_process_rank_one_or_two_observation": { "total": 0.001499514999522944, "count": 8, "is_parallel": true, "self": 0.001499514999522944 } } }, "UnityEnvironment.step": { "total": 0.04606223600012527, "count": 1, "is_parallel": true, "self": 0.00064593800016155, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004658419998122554, "count": 1, "is_parallel": true, "self": 0.0004658419998122554 }, "communicator.exchange": { "total": 0.043250763999822084, "count": 1, "is_parallel": true, "self": 0.043250763999822084 }, "steps_from_proto": { "total": 0.001699692000329378, "count": 1, "is_parallel": true, "self": 0.00037074000101711135, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013289519993122667, "count": 8, "is_parallel": true, "self": 0.0013289519993122667 } } } } } } }, "UnityEnvironment.step": { "total": 1214.8567579990722, "count": 63514, "is_parallel": true, "self": 34.060215029908704, "children": { "UnityEnvironment._generate_step_input": { "total": 23.15129520910432, "count": 63514, "is_parallel": true, "self": 23.15129520910432 }, "communicator.exchange": { "total": 1060.2567209250606, "count": 63514, "is_parallel": true, "self": 1060.2567209250606 }, "steps_from_proto": { "total": 97.38852683499863, "count": 63514, "is_parallel": true, "self": 20.027889587983736, "children": { "_process_rank_one_or_two_observation": { "total": 77.36063724701489, "count": 508112, "is_parallel": true, "self": 77.36063724701489 } } } } } } } } } } }, "trainer_advance": { "total": 643.6025039929918, "count": 63515, "self": 2.7698169819805116, "children": { "process_trajectory": { "total": 128.90282602000934, "count": 63515, "self": 128.70868201200938, "children": { "RLTrainer._checkpoint": { "total": 0.19414400799996656, "count": 2, "self": 0.19414400799996656 } } }, "_update_policy": { "total": 511.929860991002, "count": 445, "self": 305.6366285659792, "children": { "TorchPPOOptimizer.update": { "total": 206.29323242502278, "count": 22779, "self": 206.29323242502278 } } } } } } }, "trainer_threads": { "total": 1.02400008472614e-06, "count": 1, "self": 1.02400008472614e-06 }, "TrainerController._save_models": { "total": 0.08705235799970978, "count": 1, "self": 0.0014264490000641672, "children": { "RLTrainer._checkpoint": { "total": 0.08562590899964562, "count": 1, "self": 0.08562590899964562 } } } } } } }