{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054062366485596, "min": 1.4054062366485596, "max": 1.4260348081588745, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71244.2578125, "min": 68457.390625, "max": 77435.1796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 79.97893030794165, "min": 75.66666666666667, "max": 381.8320610687023, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49347.0, "min": 49060.0, "max": 50020.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999955.0, "min": 49576.0, "max": 1999955.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999955.0, "min": 49576.0, "max": 1999955.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5111145973205566, "min": 0.04072132706642151, "max": 2.5111145973205566, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1549.357666015625, "min": 5.2937726974487305, "max": 1598.174560546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.919993152881171, "min": 1.7121753098872992, "max": 3.9598596801076615, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2418.6357753276825, "min": 222.5827902853489, "max": 2475.9113156199455, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.919993152881171, "min": 1.7121753098872992, "max": 3.9598596801076615, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2418.6357753276825, "min": 222.5827902853489, "max": 2475.9113156199455, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016595346343819983, "min": 0.013075374288018794, "max": 0.02113681351984269, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04978603903145995, "min": 0.026150748576037587, "max": 0.057051010337742514, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.062043482686082514, "min": 0.022148926462978124, "max": 0.06488966513425111, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18613044805824755, "min": 0.04429785292595625, "max": 0.19206593148410323, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3220488926833388e-06, "min": 3.3220488926833388e-06, "max": 0.000295275376574875, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.966146678050017e-06, "min": 9.966146678050017e-06, "max": 0.0008441461686179499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110731666666671, "min": 0.10110731666666671, "max": 0.19842512500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033219500000001, "min": 0.2074395, "max": 0.58138205, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.52551016666668e-05, "min": 6.52551016666668e-05, "max": 0.0049214137375000015, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001957653050000004, "min": 0.0001957653050000004, "max": 0.014070964294999998, "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": "1704305329", "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=HuggyJD --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704307762" }, "total": 2432.757931645, "count": 1, "self": 0.44294718200035277, "children": { "run_training.setup": { "total": 0.049175547999993796, "count": 1, "self": 0.049175547999993796 }, "TrainerController.start_learning": { "total": 2432.265808915, "count": 1, "self": 4.501999238997996, "children": { "TrainerController._reset_env": { "total": 3.372817477999888, "count": 1, "self": 3.372817477999888 }, "TrainerController.advance": { "total": 2424.2814257820023, "count": 232512, "self": 4.770704554968233, "children": { "env_step": { "total": 1935.6345323110456, "count": 232512, "self": 1610.6605289382032, "children": { "SubprocessEnvManager._take_step": { "total": 322.0721852038605, "count": 232512, "self": 17.011374030868637, "children": { "TorchPolicy.evaluate": { "total": 305.06081117299186, "count": 222930, "self": 305.06081117299186 } } }, "workers": { "total": 2.9018181689818903, "count": 232512, "self": 0.0, "children": { "worker_root": { "total": 2425.0169397258996, "count": 232512, "is_parallel": true, "self": 1116.6631964399314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00064104199987014, "count": 1, "is_parallel": true, "self": 0.00021093200007271662, "children": { "_process_rank_one_or_two_observation": { "total": 0.00043010999979742337, "count": 2, "is_parallel": true, "self": 0.00043010999979742337 } } }, "UnityEnvironment.step": { "total": 0.055628719999958776, "count": 1, "is_parallel": true, "self": 0.0003577170002699859, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019029699979000725, "count": 1, "is_parallel": true, "self": 0.00019029699979000725 }, "communicator.exchange": { "total": 0.0542164060000232, "count": 1, "is_parallel": true, "self": 0.0542164060000232 }, "steps_from_proto": { "total": 0.000864299999875584, "count": 1, "is_parallel": true, "self": 0.00035860099978890503, "children": { "_process_rank_one_or_two_observation": { "total": 0.000505699000086679, "count": 2, "is_parallel": true, "self": 0.000505699000086679 } } } } } } }, "UnityEnvironment.step": { "total": 1308.3537432859682, "count": 232511, "is_parallel": true, "self": 41.11714015592793, "children": { "UnityEnvironment._generate_step_input": { "total": 85.25364128706792, "count": 232511, "is_parallel": true, "self": 85.25364128706792 }, "communicator.exchange": { "total": 1090.129317572971, "count": 232511, "is_parallel": true, "self": 1090.129317572971 }, "steps_from_proto": { "total": 91.85364427000127, "count": 232511, "is_parallel": true, "self": 33.734073518743344, "children": { "_process_rank_one_or_two_observation": { "total": 58.119570751257925, "count": 465022, "is_parallel": true, "self": 58.119570751257925 } } } } } } } } } } }, "trainer_advance": { "total": 483.8761889159887, "count": 232512, "self": 6.785567437977079, "children": { "process_trajectory": { "total": 152.56831444901354, "count": 232512, "self": 151.25819092901293, "children": { "RLTrainer._checkpoint": { "total": 1.3101235200006158, "count": 10, "self": 1.3101235200006158 } } }, "_update_policy": { "total": 324.52230702899806, "count": 97, "self": 261.4601203809998, "children": { "TorchPPOOptimizer.update": { "total": 63.06218664799826, "count": 2910, "self": 63.06218664799826 } } } } } } }, "trainer_threads": { "total": 1.0799999472510535e-06, "count": 1, "self": 1.0799999472510535e-06 }, "TrainerController._save_models": { "total": 0.10956533599983231, "count": 1, "self": 0.0019027909997930692, "children": { "RLTrainer._checkpoint": { "total": 0.10766254500003924, "count": 1, "self": 0.10766254500003924 } } } } } } }