{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4027190208435059, "min": 1.4027190208435059, "max": 1.4248894453048706, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68924.0, "min": 68833.203125, "max": 77404.5, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.78056951423785, "min": 73.76096822995461, "max": 400.8, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49420.0, "min": 48756.0, "max": 50100.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999908.0, "min": 49732.0, "max": 1999908.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999908.0, "min": 49732.0, "max": 1999908.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.499207019805908, "min": -0.04495975002646446, "max": 2.5531363487243652, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1492.026611328125, "min": -5.575008869171143, "max": 1657.3248291015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8214621169483243, "min": 1.7845443653002862, "max": 4.131055483924947, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2281.4128838181496, "min": 221.2835012972355, "max": 2610.9563172459602, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8214621169483243, "min": 1.7845443653002862, "max": 4.131055483924947, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2281.4128838181496, "min": 221.2835012972355, "max": 2610.9563172459602, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019057211323848203, "min": 0.011506654602756801, "max": 0.01959760335092824, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05717163397154461, "min": 0.023013309205513602, "max": 0.05717163397154461, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05782485124137667, "min": 0.024408646828184527, "max": 0.06296857818961143, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17347455372413, "min": 0.048817293656369054, "max": 0.18381293440858523, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6058987980666705e-06, "min": 3.6058987980666705e-06, "max": 0.00029526502657832495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0817696394200012e-05, "min": 1.0817696394200012e-05, "max": 0.0008437711687429498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120193333333334, "min": 0.10120193333333334, "max": 0.19842167500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30360580000000004, "min": 0.20758855, "max": 0.5812570499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.99764733333334e-05, "min": 6.99764733333334e-05, "max": 0.0049212415824999994, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002099294200000002, "min": 0.0002099294200000002, "max": 0.014064726795000001, "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": "1687670630", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687673152" }, "total": 2522.0774651290003, "count": 1, "self": 0.8382027290003862, "children": { "run_training.setup": { "total": 0.04166321799993966, "count": 1, "self": 0.04166321799993966 }, "TrainerController.start_learning": { "total": 2521.197599182, "count": 1, "self": 4.571151830026338, "children": { "TrainerController._reset_env": { "total": 5.13458541, "count": 1, "self": 5.13458541 }, "TrainerController.advance": { "total": 2511.3092714669733, "count": 233044, "self": 4.687755955915691, "children": { "env_step": { "total": 1972.0833368450278, "count": 233044, "self": 1668.778022373985, "children": { "SubprocessEnvManager._take_step": { "total": 300.3822948430684, "count": 233044, "self": 17.444410762985058, "children": { "TorchPolicy.evaluate": { "total": 282.93788408008334, "count": 222931, "self": 282.93788408008334 } } }, "workers": { "total": 2.923019627974327, "count": 233044, "self": 0.0, "children": { "worker_root": { "total": 2512.9904457770153, "count": 233044, "is_parallel": true, "self": 1148.7162979820018, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009521270000050208, "count": 1, "is_parallel": true, "self": 0.0002552950001017962, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006968319999032246, "count": 2, "is_parallel": true, "self": 0.0006968319999032246 } } }, "UnityEnvironment.step": { "total": 0.049876895000011245, "count": 1, "is_parallel": true, "self": 0.00029962200017052965, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026596599991535186, "count": 1, "is_parallel": true, "self": 0.00026596599991535186 }, "communicator.exchange": { "total": 0.048603715000012926, "count": 1, "is_parallel": true, "self": 0.048603715000012926 }, "steps_from_proto": { "total": 0.000707591999912438, "count": 1, "is_parallel": true, "self": 0.00021816099990701332, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004894310000054247, "count": 2, "is_parallel": true, "self": 0.0004894310000054247 } } } } } } }, "UnityEnvironment.step": { "total": 1364.2741477950135, "count": 233043, "is_parallel": true, "self": 39.05407635314327, "children": { "UnityEnvironment._generate_step_input": { "total": 85.85383712905343, "count": 233043, "is_parallel": true, "self": 85.85383712905343 }, "communicator.exchange": { "total": 1139.9556961728713, "count": 233043, "is_parallel": true, "self": 1139.9556961728713 }, "steps_from_proto": { "total": 99.41053813994563, "count": 233043, "is_parallel": true, "self": 38.239625706982565, "children": { "_process_rank_one_or_two_observation": { "total": 61.170912432963064, "count": 466086, "is_parallel": true, "self": 61.170912432963064 } } } } } } } } } } }, "trainer_advance": { "total": 534.5381786660297, "count": 233044, "self": 6.5276550630475185, "children": { "process_trajectory": { "total": 147.76235528198185, "count": 233044, "self": 146.36362493398246, "children": { "RLTrainer._checkpoint": { "total": 1.3987303479993898, "count": 10, "self": 1.3987303479993898 } } }, "_update_policy": { "total": 380.2481683210003, "count": 97, "self": 320.7795419479969, "children": { "TorchPPOOptimizer.update": { "total": 59.46862637300342, "count": 2910, "self": 59.46862637300342 } } } } } } }, "trainer_threads": { "total": 1.4440001905313693e-06, "count": 1, "self": 1.4440001905313693e-06 }, "TrainerController._save_models": { "total": 0.18258903100013413, "count": 1, "self": 0.00255981200007227, "children": { "RLTrainer._checkpoint": { "total": 0.18002921900006186, "count": 1, "self": 0.18002921900006186 } } } } } } }