{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4030237197875977, "min": 1.4030237197875977, "max": 1.4262008666992188, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70027.71875, "min": 68910.09375, "max": 76264.5625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.2003367003367, "min": 80.12662337662337, "max": 412.2295081967213, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49421.0, "min": 49021.0, "max": 50292.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999949.0, "min": 49761.0, "max": 1999949.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999949.0, "min": 49761.0, "max": 1999949.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4034643173217773, "min": -0.0365985669195652, "max": 2.4665679931640625, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1427.6578369140625, "min": -4.428426742553711, "max": 1474.06787109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.739565551080286, "min": 1.9142847685528195, "max": 3.9997414581842357, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2221.30193734169, "min": 231.62845699489117, "max": 2350.759249150753, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.739565551080286, "min": 1.9142847685528195, "max": 3.9997414581842357, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2221.30193734169, "min": 231.62845699489117, "max": 2350.759249150753, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015822552545513544, "min": 0.014116925898512515, "max": 0.020038159958009297, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04746765763654063, "min": 0.02823385179702503, "max": 0.05874287165703815, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05591664570901129, "min": 0.024353692090759674, "max": 0.0615769313648343, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16774993712703387, "min": 0.04870738418151935, "max": 0.18073378478487334, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7164987611999967e-06, "min": 3.7164987611999967e-06, "max": 0.000295294576568475, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.114949628359999e-05, "min": 1.114949628359999e-05, "max": 0.0008439171186943, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012388, "min": 0.1012388, "max": 0.19843152499999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037164, "min": 0.20763800000000004, "max": 0.5813056999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.181611999999996e-05, "min": 7.181611999999996e-05, "max": 0.004921733097499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021544835999999986, "min": 0.00021544835999999986, "max": 0.014067154429999998, "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": "1703770488", "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 --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": "1703773043" }, "total": 2554.7474165080002, "count": 1, "self": 0.4493222810001498, "children": { "run_training.setup": { "total": 0.05066931900000782, "count": 1, "self": 0.05066931900000782 }, "TrainerController.start_learning": { "total": 2554.247424908, "count": 1, "self": 5.061562270127524, "children": { "TrainerController._reset_env": { "total": 3.3083332500000324, "count": 1, "self": 3.3083332500000324 }, "TrainerController.advance": { "total": 2545.763215133873, "count": 232616, "self": 4.993378686880533, "children": { "env_step": { "total": 2007.8718463920775, "count": 232616, "self": 1669.735419705085, "children": { "SubprocessEnvManager._take_step": { "total": 334.97897361998264, "count": 232616, "self": 17.612594676036338, "children": { "TorchPolicy.evaluate": { "total": 317.3663789439463, "count": 222906, "self": 317.3663789439463 } } }, "workers": { "total": 3.157453067009783, "count": 232616, "self": 0.0, "children": { "worker_root": { "total": 2546.584570847949, "count": 232616, "is_parallel": true, "self": 1192.0404469320429, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006587150000996189, "count": 1, "is_parallel": true, "self": 0.00018551600010141556, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047319899999820336, "count": 2, "is_parallel": true, "self": 0.00047319899999820336 } } }, "UnityEnvironment.step": { "total": 0.03189561199997115, "count": 1, "is_parallel": true, "self": 0.0003589520000559787, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019822399997337925, "count": 1, "is_parallel": true, "self": 0.00019822399997337925 }, "communicator.exchange": { "total": 0.030446938999943995, "count": 1, "is_parallel": true, "self": 0.030446938999943995 }, "steps_from_proto": { "total": 0.0008914969999977984, "count": 1, "is_parallel": true, "self": 0.00036716699992211943, "children": { "_process_rank_one_or_two_observation": { "total": 0.000524330000075679, "count": 2, "is_parallel": true, "self": 0.000524330000075679 } } } } } } }, "UnityEnvironment.step": { "total": 1354.5441239159063, "count": 232615, "is_parallel": true, "self": 42.69363058495719, "children": { "UnityEnvironment._generate_step_input": { "total": 85.37074384488551, "count": 232615, "is_parallel": true, "self": 85.37074384488551 }, "communicator.exchange": { "total": 1130.8984807030474, "count": 232615, "is_parallel": true, "self": 1130.8984807030474 }, "steps_from_proto": { "total": 95.5812687830163, "count": 232615, "is_parallel": true, "self": 32.90584734517449, "children": { "_process_rank_one_or_two_observation": { "total": 62.675421437841806, "count": 465230, "is_parallel": true, "self": 62.675421437841806 } } } } } } } } } } }, "trainer_advance": { "total": 532.8979900549152, "count": 232616, "self": 7.4746285100351315, "children": { "process_trajectory": { "total": 164.27737083688191, "count": 232616, "self": 163.03485592988227, "children": { "RLTrainer._checkpoint": { "total": 1.242514906999645, "count": 10, "self": 1.242514906999645 } } }, "_update_policy": { "total": 361.1459907079982, "count": 97, "self": 293.72774436099974, "children": { "TorchPPOOptimizer.update": { "total": 67.41824634699844, "count": 2910, "self": 67.41824634699844 } } } } } } }, "trainer_threads": { "total": 1.1359998097759672e-06, "count": 1, "self": 1.1359998097759672e-06 }, "TrainerController._save_models": { "total": 0.1143131179996999, "count": 1, "self": 0.002260234000004857, "children": { "RLTrainer._checkpoint": { "total": 0.11205288399969504, "count": 1, "self": 0.11205288399969504 } } } } } } }