{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4028607606887817, "min": 1.4028607606887817, "max": 1.4290721416473389, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70123.3984375, "min": 69222.1640625, "max": 77580.796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.66469428007889, "min": 71.32225433526011, "max": 396.968253968254, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49516.0, "min": 48994.0, "max": 50022.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999965.0, "min": 49394.0, "max": 1999965.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999965.0, "min": 49394.0, "max": 1999965.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.380669593811035, "min": 0.15651057660579681, "max": 2.5372209548950195, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1206.99951171875, "min": 19.56382179260254, "max": 1683.427490234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.586053985345528, "min": 1.7925045390129088, "max": 4.076568033762436, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1818.1293705701828, "min": 224.06306737661362, "max": 2705.291987478733, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.586053985345528, "min": 1.7925045390129088, "max": 4.076568033762436, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1818.1293705701828, "min": 224.06306737661362, "max": 2705.291987478733, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013561604568945363, "min": 0.012935729412897166, "max": 0.021170887675705467, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04068481370683609, "min": 0.027123285039609375, "max": 0.0635126630271164, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053156503041585285, "min": 0.01931445418546597, "max": 0.057887609799702956, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15946950912475585, "min": 0.03862890837093194, "max": 0.17366282939910888, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.800298733266664e-06, "min": 3.800298733266664e-06, "max": 0.00029534115155294995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1400896199799992e-05, "min": 1.1400896199799992e-05, "max": 0.000844191018603, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126673333333334, "min": 0.10126673333333334, "max": 0.19844704999999999, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038002, "min": 0.20766570000000006, "max": 0.5813969999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.320999333333332e-05, "min": 7.320999333333332e-05, "max": 0.004922507795000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021962997999999995, "min": 0.00021962997999999995, "max": 0.014071710300000002, "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": "1712938374", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712940794" }, "total": 2420.01796725, "count": 1, "self": 0.4403686200002994, "children": { "run_training.setup": { "total": 0.05308558899992022, "count": 1, "self": 0.05308558899992022 }, "TrainerController.start_learning": { "total": 2419.524513041, "count": 1, "self": 4.309786900042127, "children": { "TrainerController._reset_env": { "total": 2.7827746340000203, "count": 1, "self": 2.7827746340000203 }, "TrainerController.advance": { "total": 2412.3147598729574, "count": 233016, "self": 4.671034480009894, "children": { "env_step": { "total": 1933.1764791620017, "count": 233016, "self": 1604.6557949059847, "children": { "SubprocessEnvManager._take_step": { "total": 325.64917127002343, "count": 233016, "self": 17.076084435992698, "children": { "TorchPolicy.evaluate": { "total": 308.57308683403073, "count": 223002, "self": 308.57308683403073 } } }, "workers": { "total": 2.8715129859934905, "count": 233016, "self": 0.0, "children": { "worker_root": { "total": 2412.044565717866, "count": 233016, "is_parallel": true, "self": 1115.1928002949012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008881879999762532, "count": 1, "is_parallel": true, "self": 0.00023868800008131075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006494999998949424, "count": 2, "is_parallel": true, "self": 0.0006494999998949424 } } }, "UnityEnvironment.step": { "total": 0.02952738600004068, "count": 1, "is_parallel": true, "self": 0.00037359800001013355, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020704300004581455, "count": 1, "is_parallel": true, "self": 0.00020704300004581455 }, "communicator.exchange": { "total": 0.028191958999968847, "count": 1, "is_parallel": true, "self": 0.028191958999968847 }, "steps_from_proto": { "total": 0.0007547860000158835, "count": 1, "is_parallel": true, "self": 0.0002076399998713896, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005471460001444939, "count": 2, "is_parallel": true, "self": 0.0005471460001444939 } } } } } } }, "UnityEnvironment.step": { "total": 1296.851765422965, "count": 233015, "is_parallel": true, "self": 39.49437468397059, "children": { "UnityEnvironment._generate_step_input": { "total": 85.53948385607714, "count": 233015, "is_parallel": true, "self": 85.53948385607714 }, "communicator.exchange": { "total": 1079.0095371639554, "count": 233015, "is_parallel": true, "self": 1079.0095371639554 }, "steps_from_proto": { "total": 92.80836971896179, "count": 233015, "is_parallel": true, "self": 35.24195292984257, "children": { "_process_rank_one_or_two_observation": { "total": 57.566416789119216, "count": 466030, "is_parallel": true, "self": 57.566416789119216 } } } } } } } } } } }, "trainer_advance": { "total": 474.46724623094576, "count": 233016, "self": 6.4669706699462495, "children": { "process_trajectory": { "total": 157.81375376299843, "count": 233016, "self": 156.48465897999802, "children": { "RLTrainer._checkpoint": { "total": 1.3290947830004143, "count": 10, "self": 1.3290947830004143 } } }, "_update_policy": { "total": 310.1865217980011, "count": 97, "self": 249.8246006000012, "children": { "TorchPPOOptimizer.update": { "total": 60.36192119799989, "count": 2910, "self": 60.36192119799989 } } } } } } }, "trainer_threads": { "total": 9.360001058666967e-07, "count": 1, "self": 9.360001058666967e-07 }, "TrainerController._save_models": { "total": 0.11719069800028592, "count": 1, "self": 0.0020154690000708797, "children": { "RLTrainer._checkpoint": { "total": 0.11517522900021504, "count": 1, "self": 0.11517522900021504 } } } } } } }