{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44939202070236206, "min": 0.44939202070236206, "max": 1.5252050161361694, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13395.4775390625, "min": 13395.4775390625, "max": 46268.62109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.35140782594680786, "min": -0.1544630527496338, "max": 0.41823187470436096, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 92.06884765625, "min": -36.60774230957031, "max": 111.24967956542969, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0003275316266808659, "min": -0.07812140882015228, "max": 0.33654555678367615, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.08581328392028809, "min": -19.374109268188477, "max": 79.76129913330078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06697454845319348, "min": 0.0667907748965233, "max": 0.07444530798603849, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9376436783447086, "min": 0.49177110363343246, "max": 1.046869448979908, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01360124689779782, "min": 0.0008053525699171809, "max": 0.014575872917339437, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19041745656916947, "min": 0.00885887826908899, "max": 0.21863809376009155, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.504383212857144e-06, "min": 7.504383212857144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010506136498000001, "min": 0.00010506136498000001, "max": 0.0035076548307817995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250142857142856, "min": 0.10250142857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.43502, "min": 1.3886848, "max": 2.6174335, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025989271428571435, "min": 0.00025989271428571435, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036384980000000013, "min": 0.0036384980000000013, "max": 0.11694489818000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00886375643312931, "min": 0.00886375643312931, "max": 0.3292976915836334, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12409259378910065, "min": 0.12409259378910065, "max": 2.305083751678467, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 459.5593220338983, "min": 458.04615384615386, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27114.0, "min": 15984.0, "max": 32336.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3709050593739849, "min": -1.0000000521540642, "max": 1.4996399771708708, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 80.88339850306511, "min": -30.36800166964531, "max": 97.4765985161066, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3709050593739849, "min": -1.0000000521540642, "max": 1.4996399771708708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 80.88339850306511, "min": -30.36800166964531, "max": 97.4765985161066, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04199293626855143, "min": 0.04199293626855143, "max": 6.592508281581104, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4775832398445345, "min": 2.4775832398445345, "max": 105.48013250529766, "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": "1714279682", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714282666" }, "total": 2984.2072578219995, "count": 1, "self": 0.604306872000052, "children": { "run_training.setup": { "total": 0.0744351750001897, "count": 1, "self": 0.0744351750001897 }, "TrainerController.start_learning": { "total": 2983.5285157749995, "count": 1, "self": 2.0907648469046762, "children": { "TrainerController._reset_env": { "total": 3.7656844850000653, "count": 1, "self": 3.7656844850000653 }, "TrainerController.advance": { "total": 2977.586832378095, "count": 63522, "self": 2.322114338117899, "children": { "env_step": { "total": 1926.9238651200433, "count": 63522, "self": 1762.6322024141646, "children": { "SubprocessEnvManager._take_step": { "total": 162.92325058593156, "count": 63522, "self": 6.65981573695035, "children": { "TorchPolicy.evaluate": { "total": 156.2634348489812, "count": 62559, "self": 156.2634348489812 } } }, "workers": { "total": 1.368412119947152, "count": 63522, "self": 0.0, "children": { "worker_root": { "total": 2977.9489710829826, "count": 63522, "is_parallel": true, "self": 1389.7699111280165, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009858735000079832, "count": 1, "is_parallel": true, "self": 0.007714782999528325, "children": { "_process_rank_one_or_two_observation": { "total": 0.002143952000551508, "count": 8, "is_parallel": true, "self": 0.002143952000551508 } } }, "UnityEnvironment.step": { "total": 0.11259582699995008, "count": 1, "is_parallel": true, "self": 0.000743018999855849, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005049179999332409, "count": 1, "is_parallel": true, "self": 0.0005049179999332409 }, "communicator.exchange": { "total": 0.10927057300000342, "count": 1, "is_parallel": true, "self": 0.10927057300000342 }, "steps_from_proto": { "total": 0.0020773170001575636, "count": 1, "is_parallel": true, "self": 0.00039857999990999815, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016787370002475654, "count": 8, "is_parallel": true, "self": 0.0016787370002475654 } } } } } } }, "UnityEnvironment.step": { "total": 1588.179059954966, "count": 63521, "is_parallel": true, "self": 47.65702234510786, "children": { "UnityEnvironment._generate_step_input": { "total": 26.89005414893427, "count": 63521, "is_parallel": true, "self": 26.89005414893427 }, "communicator.exchange": { "total": 1385.524374842927, "count": 63521, "is_parallel": true, "self": 1385.524374842927 }, "steps_from_proto": { "total": 128.1076086179969, "count": 63521, "is_parallel": true, "self": 27.156946448944154, "children": { "_process_rank_one_or_two_observation": { "total": 100.95066216905275, "count": 508168, "is_parallel": true, "self": 100.95066216905275 } } } } } } } } } } }, "trainer_advance": { "total": 1048.3408529199342, "count": 63522, "self": 4.394893165977237, "children": { "process_trajectory": { "total": 158.21512669396589, "count": 63522, "self": 157.98151352196646, "children": { "RLTrainer._checkpoint": { "total": 0.23361317199942278, "count": 2, "self": 0.23361317199942278 } } }, "_update_policy": { "total": 885.730833059991, "count": 450, "self": 356.9090808790195, "children": { "TorchPPOOptimizer.update": { "total": 528.8217521809715, "count": 22794, "self": 528.8217521809715 } } } } } } }, "trainer_threads": { "total": 8.950000847107731e-07, "count": 1, "self": 8.950000847107731e-07 }, "TrainerController._save_models": { "total": 0.08523316999981034, "count": 1, "self": 0.002110393999828375, "children": { "RLTrainer._checkpoint": { "total": 0.08312277599998197, "count": 1, "self": 0.08312277599998197 } } } } } } }