{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5035707950592041, "min": 0.49614259600639343, "max": 1.4029970169067383, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 15179.6376953125, "min": 14836.6484375, "max": 42561.31640625, "count": 34 }, "Pyramids.Step.mean": { "value": 1019995.0, "min": 29952.0, "max": 1019995.0, "count": 34 }, "Pyramids.Step.sum": { "value": 1019995.0, "min": 29952.0, "max": 1019995.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6433641910552979, "min": -0.14291712641716003, "max": 0.6433641910552979, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.0720672607422, "min": -34.30010986328125, "max": 182.0720672607422, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014951402321457863, "min": -0.019025901332497597, "max": 0.3197302222251892, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.2312469482421875, "min": -5.270174503326416, "max": 76.7352523803711, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06990049004421701, "min": 0.06516248699011792, "max": 0.07387510530195328, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9786068606190382, "min": 0.48788912784948485, "max": 1.062189653220212, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013659507115205216, "min": 0.00043308939464650997, "max": 0.015288338250001561, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19123309961287302, "min": 0.005382583316498735, "max": 0.22655539464418933, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001995075977831929, "min": 0.0001995075977831929, "max": 0.00029838354339596195, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027931063689647004, "min": 0.0020886848037717336, "max": 0.004027346557551199, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16650252142857142, "min": 0.16650252142857142, "max": 0.19946118095238097, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3310353, "min": 1.3962282666666668, "max": 2.8424488000000006, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 0.0066536018907142865, "min": 0.0066536018907142865, "max": 0.009946171977142856, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.09315042647, "min": 0.06962320384, "max": 0.13426063512, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009614775888621807, "min": 0.009268582798540592, "max": 0.5127269625663757, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13460686802864075, "min": 0.12976016104221344, "max": 3.5890886783599854, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 321.9894736842105, "min": 321.9894736842105, "max": 999.0, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30589.0, "min": 15984.0, "max": 33615.0, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.635892610016622, "min": -1.0000000521540642, "max": 1.6447894586544287, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 155.4097979515791, "min": -31.996001675724983, "max": 158.48499850928783, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.635892610016622, "min": -1.0000000521540642, "max": 1.6447894586544287, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 155.4097979515791, "min": -31.996001675724983, "max": 158.48499850928783, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031865211179951745, "min": 0.031865211179951745, "max": 10.910333191975951, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 3.027195062095416, "min": 2.498875974561088, "max": 174.56533107161522, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687101573", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687104777" }, "total": 3204.3454685569995, "count": 1, "self": 0.7711712169993916, "children": { "run_training.setup": { "total": 0.07415090400013469, "count": 1, "self": 0.07415090400013469 }, "TrainerController.start_learning": { "total": 3203.5001464360003, "count": 1, "self": 2.2728705510417058, "children": { "TrainerController._reset_env": { "total": 2.0098718950000602, "count": 1, "self": 2.0098718950000602 }, "TrainerController.advance": { "total": 3198.8436246129586, "count": 66009, "self": 2.3754942999439663, "children": { "env_step": { "total": 2098.283074378045, "count": 66009, "self": 1962.9037970630668, "children": { "SubprocessEnvManager._take_step": { "total": 134.01638035691735, "count": 66009, "self": 6.635274074977133, "children": { "TorchPolicy.evaluate": { "total": 127.38110628194022, "count": 64845, "self": 127.38110628194022 } } }, "workers": { "total": 1.362896958060901, "count": 66008, "self": 0.0, "children": { "worker_root": { "total": 3196.9963219091132, "count": 66008, "is_parallel": true, "self": 1398.5003774381582, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003955057999974088, "count": 1, "is_parallel": true, "self": 0.0011848260000988375, "children": { "_process_rank_one_or_two_observation": { "total": 0.00277023199987525, "count": 8, "is_parallel": true, "self": 0.00277023199987525 } } }, "UnityEnvironment.step": { "total": 0.08365129699996032, "count": 1, "is_parallel": true, "self": 0.0006793240002025414, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006363459999647603, "count": 1, "is_parallel": true, "self": 0.0006363459999647603 }, "communicator.exchange": { "total": 0.07980633499983014, "count": 1, "is_parallel": true, "self": 0.07980633499983014 }, "steps_from_proto": { "total": 0.0025292919999628793, "count": 1, "is_parallel": true, "self": 0.0004932789997837972, "children": { "_process_rank_one_or_two_observation": { "total": 0.002036013000179082, "count": 8, "is_parallel": true, "self": 0.002036013000179082 } } } } } } }, "UnityEnvironment.step": { "total": 1798.495944470955, "count": 66007, "is_parallel": true, "self": 45.25140565587685, "children": { "UnityEnvironment._generate_step_input": { "total": 24.208042473026353, "count": 66007, "is_parallel": true, "self": 24.208042473026353 }, "communicator.exchange": { "total": 1592.5223331440711, "count": 66007, "is_parallel": true, "self": 1592.5223331440711 }, "steps_from_proto": { "total": 136.51416319798068, "count": 66007, "is_parallel": true, "self": 28.78706968786196, "children": { "_process_rank_one_or_two_observation": { "total": 107.72709351011872, "count": 528056, "is_parallel": true, "self": 107.72709351011872 } } } } } } } } } } }, "trainer_advance": { "total": 1098.1850559349696, "count": 66008, "self": 4.065363378085294, "children": { "process_trajectory": { "total": 140.51066329088644, "count": 66008, "self": 140.19544902088683, "children": { "RLTrainer._checkpoint": { "total": 0.31521426999961477, "count": 2, "self": 0.31521426999961477 } } }, "_update_policy": { "total": 953.6090292659978, "count": 463, "self": 416.2596897320004, "children": { "TorchPPOOptimizer.update": { "total": 537.3493395339974, "count": 23664, "self": 537.3493395339974 } } } } } } }, "trainer_threads": { "total": 1.897999936772976e-06, "count": 1, "self": 1.897999936772976e-06 }, "TrainerController._save_models": { "total": 0.37377747899972746, "count": 1, "self": 0.00892455999928643, "children": { "RLTrainer._checkpoint": { "total": 0.36485291900044103, "count": 1, "self": 0.36485291900044103 } } } } } } }