{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18241113424301147, "min": 0.17553913593292236, "max": 1.462368369102478, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5484.00830078125, "min": 5283.02587890625, "max": 44362.40625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999997.0, "min": 29952.0, "max": 2999997.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999997.0, "min": 29952.0, "max": 2999997.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.740119457244873, "min": -0.11213929206132889, "max": 0.8858107924461365, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 216.11488342285156, "min": -27.025569915771484, "max": 274.6013488769531, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0033551144879311323, "min": -0.009812302887439728, "max": 0.3880610764026642, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9796934127807617, "min": -2.786694049835205, "max": 91.97047424316406, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07191398710532118, "min": 0.06216856511448333, "max": 0.07381847566450582, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0787098065798177, "min": 0.4634910679269105, "max": 1.102303517885351, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014725369274170364, "min": 0.00012122709488227262, "max": 0.016774175830862218, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22088053911255545, "min": 0.0014547251385872715, "max": 0.25087500642014976, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5079261640577785e-06, "min": 1.5079261640577785e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.261889246086668e-05, "min": 2.261889246086668e-05, "max": 0.0037167937610688, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050260888888891, "min": 0.10050260888888891, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075391333333337, "min": 1.3757013333333334, "max": 2.6624918666666666, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.021062800000001e-05, "min": 6.021062800000001e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009031594200000002, "min": 0.0009031594200000002, "max": 0.12390922687999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006614855956286192, "min": 0.0062143439427018166, "max": 0.3955007493495941, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09922283887863159, "min": 0.08712960034608841, "max": 2.768505334854126, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 251.552, "min": 202.91156462585033, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31444.0, "min": 15984.0, "max": 34286.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6844303804636, "min": -1.0000000521540642, "max": 1.7970884214250409, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 210.55379755795002, "min": -32.000001668930054, "max": 264.171997949481, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6844303804636, "min": -1.0000000521540642, "max": 1.7970884214250409, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 210.55379755795002, "min": -32.000001668930054, "max": 264.171997949481, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017258611753815784, "min": 0.014170273214991775, "max": 8.26679853349924, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.157326469226973, "min": 1.854908403052832, "max": 132.26877653598785, "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": "1680459146", "python_version": "3.8.12 | packaged by conda-forge | (default, Sep 29 2021, 19:50:30) \n[GCC 9.4.0]", "command_line_arguments": "/home/jason/miniconda3/envs/rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.0", "numpy_version": "1.19.2", "end_time_seconds": "1680467030" }, "total": 7884.0850688405335, "count": 1, "self": 0.21858591213822365, "children": { "run_training.setup": { "total": 0.010346829891204834, "count": 1, "self": 0.010346829891204834 }, "TrainerController.start_learning": { "total": 7883.856136098504, "count": 1, "self": 2.9920715168118477, "children": { "TrainerController._reset_env": { "total": 1.7283909693360329, "count": 1, "self": 1.7283909693360329 }, "TrainerController.advance": { "total": 7879.069198064506, "count": 194261, "self": 2.9586508460342884, "children": { "env_step": { "total": 6279.638076741248, "count": 194261, "self": 6007.892601206899, "children": { "SubprocessEnvManager._take_step": { "total": 269.8135972842574, "count": 194261, "self": 8.162088863551617, "children": { "TorchPolicy.evaluate": { "total": 261.6515084207058, "count": 187561, "self": 114.20018028840423, "children": { "TorchPolicy.sample_actions": { "total": 147.45132813230157, "count": 187561, "self": 147.45132813230157 } } } } }, "workers": { "total": 1.931878250092268, "count": 194261, "self": 0.0, "children": { "worker_root": { "total": 7878.661277964711, "count": 194261, "is_parallel": true, "self": 2072.185051072389, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017779767513275146, "count": 1, "is_parallel": true, "self": 0.0002979859709739685, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014799907803535461, "count": 8, "is_parallel": true, "self": 0.0014799907803535461 } } }, "UnityEnvironment.step": { "total": 0.04210019111633301, "count": 1, "is_parallel": true, "self": 0.0001076236367225647, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007106959819793701, "count": 1, "is_parallel": true, "self": 0.0007106959819793701 }, "communicator.exchange": { "total": 0.03975749760866165, "count": 1, "is_parallel": true, "self": 0.03975749760866165 }, "steps_from_proto": { "total": 0.0015243738889694214, "count": 1, "is_parallel": true, "self": 0.00020407512784004211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013202987611293793, "count": 8, "is_parallel": true, "self": 0.0013202987611293793 } } } } } } }, "UnityEnvironment.step": { "total": 5806.476226892322, "count": 194260, "is_parallel": true, "self": 20.47981609776616, "children": { "UnityEnvironment._generate_step_input": { "total": 123.53412928804755, "count": 194260, "is_parallel": true, "self": 123.53412928804755 }, "communicator.exchange": { "total": 5369.357915256172, "count": 194260, "is_parallel": true, "self": 5369.357915256172 }, "steps_from_proto": { "total": 293.10436625033617, "count": 194260, "is_parallel": true, "self": 35.75217841938138, "children": { "_process_rank_one_or_two_observation": { "total": 257.3521878309548, "count": 1554080, "is_parallel": true, "self": 257.3521878309548 } } } } } } } } } } }, "trainer_advance": { "total": 1596.4724704772234, "count": 194261, "self": 5.738157641142607, "children": { "process_trajectory": { "total": 340.3344692774117, "count": 194261, "self": 339.89256013184786, "children": { "RLTrainer._checkpoint": { "total": 0.44190914556384087, "count": 6, "self": 0.44190914556384087 } } }, "_update_policy": { "total": 1250.399843558669, "count": 1370, "self": 462.2334176339209, "children": { "TorchPPOOptimizer.update": { "total": 788.1664259247482, "count": 68397, "self": 788.1664259247482 } } } } } } }, "trainer_threads": { "total": 6.48200511932373e-07, "count": 1, "self": 6.48200511932373e-07 }, "TrainerController._save_models": { "total": 0.06647489964962006, "count": 1, "self": 0.0007011406123638153, "children": { "RLTrainer._checkpoint": { "total": 0.06577375903725624, "count": 1, "self": 0.06577375903725624 } } } } } } }