{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7108353972434998, "min": 0.7108353972434998, "max": 1.4653944969177246, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 21290.94140625, "min": 21290.94140625, "max": 44454.20703125, "count": 16 }, "Pyramids.Step.mean": { "value": 479880.0, "min": 29952.0, "max": 479880.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479880.0, "min": 29952.0, "max": 479880.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05559397488832474, "min": -0.101214200258255, "max": -0.017155522480607033, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -13.398147583007812, "min": -24.595050811767578, "max": -4.151636600494385, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025730356574058533, "min": 0.025730356574058533, "max": 0.3417685329914093, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.201015949249268, "min": 6.201015949249268, "max": 82.02444458007812, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0704533419359186, "min": 0.0670096282480333, "max": 0.07391664836171882, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9863467871028604, "min": 0.5080809209247564, "max": 0.9863467871028604, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0034926668596590507, "min": 0.00011743077851133513, "max": 0.00956553349748404, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04889733603522671, "min": 0.0015266001206473566, "max": 0.06695873448238827, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.111987867435714e-05, "min": 2.111987867435714e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029567830144099994, "min": 0.00029567830144099994, "max": 0.0026073808308732004, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1070399285714286, "min": 0.1070399285714286, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4985590000000004, "min": 1.3773696000000002, "max": 2.1691268, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007132888642857144, "min": 0.0007132888642857144, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.0099860441, "min": 0.0099860441, "max": 0.08695576732, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.027406563982367516, "min": 0.027122551575303078, "max": 0.46707412600517273, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3836919069290161, "min": 0.3797157108783722, "max": 3.2695188522338867, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 915.258064516129, "min": 915.258064516129, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28373.0, "min": 15984.0, "max": 32471.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.543318800162524, "min": -1.0000000521540642, "max": -0.543318800162524, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -17.386201605200768, "min": -31.99200163781643, "max": -16.000000834465027, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.543318800162524, "min": -1.0000000521540642, "max": -0.543318800162524, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -17.386201605200768, "min": -31.99200163781643, "max": -16.000000834465027, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.26329837751109153, "min": 0.26329837751109153, "max": 9.043439206667244, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 8.425548080354929, "min": 8.370892848819494, "max": 144.6950273066759, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702162386", "python_version": "3.10.11 (main, Apr 20 2023, 19:02:41) [GCC 11.2.0]", "command_line_arguments": "/home/lab_rat/.local/bin/mlagents-learn /app/data/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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702163082" }, "total": 695.652108405001, "count": 1, "self": 0.32243540700164885, "children": { "run_training.setup": { "total": 0.02877940700000181, "count": 1, "self": 0.02877940700000181 }, "TrainerController.start_learning": { "total": 695.3008935909993, "count": 1, "self": 0.5737223478045053, "children": { "TrainerController._reset_env": { "total": 1.1567680409998502, "count": 1, "self": 1.1567680409998502 }, "TrainerController.advance": { "total": 693.3274274161959, "count": 31556, "self": 0.5533450101056587, "children": { "env_step": { "total": 445.21438054408463, "count": 31556, "self": 390.83050117718994, "children": { "SubprocessEnvManager._take_step": { "total": 53.96969126292879, "count": 31556, "self": 1.5856372378520973, "children": { "TorchPolicy.evaluate": { "total": 52.38405402507669, "count": 31312, "self": 52.38405402507669 } } }, "workers": { "total": 0.41418810396589834, "count": 31556, "self": 0.0, "children": { "worker_root": { "total": 693.9711947010674, "count": 31556, "is_parallel": true, "self": 344.16595889921336, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013636180001412868, "count": 1, "is_parallel": true, "self": 0.0003614369998103939, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010021810003308929, "count": 8, "is_parallel": true, "self": 0.0010021810003308929 } } }, "UnityEnvironment.step": { "total": 0.03674301499995636, "count": 1, "is_parallel": true, "self": 0.0003749669995158911, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028205599937791703, "count": 1, "is_parallel": true, "self": 0.00028205599937791703 }, "communicator.exchange": { "total": 0.03502371100057644, "count": 1, "is_parallel": true, "self": 0.03502371100057644 }, "steps_from_proto": { "total": 0.0010622810004861094, "count": 1, "is_parallel": true, "self": 0.00022628500028076814, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008359960002053413, "count": 8, "is_parallel": true, "self": 0.0008359960002053413 } } } } } } }, "UnityEnvironment.step": { "total": 349.805235801854, "count": 31555, "is_parallel": true, "self": 11.53983459482788, "children": { "UnityEnvironment._generate_step_input": { "total": 7.691194832119436, "count": 31555, "is_parallel": true, "self": 7.691194832119436 }, "communicator.exchange": { "total": 298.50096474902966, "count": 31555, "is_parallel": true, "self": 298.50096474902966 }, "steps_from_proto": { "total": 32.07324162587702, "count": 31555, "is_parallel": true, "self": 6.751596912053174, "children": { "_process_rank_one_or_two_observation": { "total": 25.321644713823844, "count": 252440, "is_parallel": true, "self": 25.321644713823844 } } } } } } } } } } }, "trainer_advance": { "total": 247.55970186200557, "count": 31556, "self": 0.8973886679859788, "children": { "process_trajectory": { "total": 46.018624579027346, "count": 31556, "self": 45.949586046027434, "children": { "RLTrainer._checkpoint": { "total": 0.0690385329999117, "count": 1, "self": 0.0690385329999117 } } }, "_update_policy": { "total": 200.64368861499224, "count": 205, "self": 121.97589993204019, "children": { "TorchPPOOptimizer.update": { "total": 78.66778868295205, "count": 11445, "self": 78.66778868295205 } } } } } } }, "trainer_threads": { "total": 7.999988156370819e-07, "count": 1, "self": 7.999988156370819e-07 }, "TrainerController._save_models": { "total": 0.24297498600026302, "count": 1, "self": 0.0006479320018115686, "children": { "RLTrainer._checkpoint": { "total": 0.24232705399845145, "count": 1, "self": 0.24232705399845145 } } } } } } }