{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4060252904891968, "min": 1.4060252904891968, "max": 1.429041862487793, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69662.9296875, "min": 69129.8984375, "max": 78310.5625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.12290502793296, "min": 76.75856697819314, "max": 385.77862595419845, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49470.0, "min": 48962.0, "max": 50537.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999960.0, "min": 49986.0, "max": 1999960.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999960.0, "min": 49986.0, "max": 1999960.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3751959800720215, "min": 0.06047550588846207, "max": 2.5012927055358887, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1275.480224609375, "min": 7.861815929412842, "max": 1560.0673828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.574491670899773, "min": 1.764710963001618, "max": 3.9891424012738605, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1919.502027273178, "min": 229.41242519021034, "max": 2504.1168717741966, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.574491670899773, "min": 1.764710963001618, "max": 3.9891424012738605, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1919.502027273178, "min": 229.41242519021034, "max": 2504.1168717741966, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015464788699561421, "min": 0.014153718691280421, "max": 0.02079552350526986, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04639436609868426, "min": 0.028307437382560842, "max": 0.05807890405655295, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054525612211889694, "min": 0.022885085797558227, "max": 0.06306721990307172, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16357683663566908, "min": 0.045770171595116454, "max": 0.18287649465103942, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.077298640933336e-06, "min": 4.077298640933336e-06, "max": 0.00029532120155960004, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2231895922800009e-05, "min": 1.2231895922800009e-05, "max": 0.00084408526863825, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10135906666666668, "min": 0.10135906666666668, "max": 0.19844040000000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30407720000000005, "min": 0.20784595, "max": 0.5813617499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.781742666666672e-05, "min": 7.781742666666672e-05, "max": 0.0049221759600000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00023345228000000017, "min": 0.00023345228000000017, "max": 0.014069951325, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717857588", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy-hisham --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717860105" }, "total": 2516.9462308009997, "count": 1, "self": 0.8448646199994982, "children": { "run_training.setup": { "total": 0.060542668999914895, "count": 1, "self": 0.060542668999914895 }, "TrainerController.start_learning": { "total": 2516.0408235120003, "count": 1, "self": 4.634175802123536, "children": { "TrainerController._reset_env": { "total": 3.439471135000076, "count": 1, "self": 3.439471135000076 }, "TrainerController.advance": { "total": 2507.7784274818764, "count": 232698, "self": 4.836327787832033, "children": { "env_step": { "total": 1972.5608176510407, "count": 232698, "self": 1630.871595753035, "children": { "SubprocessEnvManager._take_step": { "total": 338.72246786994697, "count": 232698, "self": 18.57327789885153, "children": { "TorchPolicy.evaluate": { "total": 320.14918997109544, "count": 222998, "self": 320.14918997109544 } } }, "workers": { "total": 2.966754028058631, "count": 232698, "self": 0.0, "children": { "worker_root": { "total": 2508.738151496945, "count": 232698, "is_parallel": true, "self": 1193.9741182759453, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010526610001306835, "count": 1, "is_parallel": true, "self": 0.00022613000010096584, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008265310000297177, "count": 2, "is_parallel": true, "self": 0.0008265310000297177 } } }, "UnityEnvironment.step": { "total": 0.03140254400000231, "count": 1, "is_parallel": true, "self": 0.00044106400014243263, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030984299996816844, "count": 1, "is_parallel": true, "self": 0.00030984299996816844 }, "communicator.exchange": { "total": 0.02983305699990524, "count": 1, "is_parallel": true, "self": 0.02983305699990524 }, "steps_from_proto": { "total": 0.0008185799999864685, "count": 1, "is_parallel": true, "self": 0.0002293719999215682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005892080000649003, "count": 2, "is_parallel": true, "self": 0.0005892080000649003 } } } } } } }, "UnityEnvironment.step": { "total": 1314.7640332209999, "count": 232697, "is_parallel": true, "self": 39.668642637945595, "children": { "UnityEnvironment._generate_step_input": { "total": 83.07491911706416, "count": 232697, "is_parallel": true, "self": 83.07491911706416 }, "communicator.exchange": { "total": 1099.9085844889921, "count": 232697, "is_parallel": true, "self": 1099.9085844889921 }, "steps_from_proto": { "total": 92.111886976998, "count": 232697, "is_parallel": true, "self": 32.62150601995813, "children": { "_process_rank_one_or_two_observation": { "total": 59.49038095703986, "count": 465394, "is_parallel": true, "self": 59.49038095703986 } } } } } } } } } } }, "trainer_advance": { "total": 530.3812820430035, "count": 232698, "self": 6.859706980906594, "children": { "process_trajectory": { "total": 161.96744874409455, "count": 232698, "self": 160.51877513109525, "children": { "RLTrainer._checkpoint": { "total": 1.4486736129993005, "count": 10, "self": 1.4486736129993005 } } }, "_update_policy": { "total": 361.5541263180023, "count": 97, "self": 294.4712422139976, "children": { "TorchPPOOptimizer.update": { "total": 67.08288410400473, "count": 2910, "self": 67.08288410400473 } } } } } } }, "trainer_threads": { "total": 1.7699999261822086e-06, "count": 1, "self": 1.7699999261822086e-06 }, "TrainerController._save_models": { "total": 0.18874732300037067, "count": 1, "self": 0.004625415000191424, "children": { "RLTrainer._checkpoint": { "total": 0.18412190800017925, "count": 1, "self": 0.18412190800017925 } } } } } } }