{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4017223119735718, "min": 1.4017223119735718, "max": 1.4268707036972046, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68650.75, "min": 67994.6484375, "max": 76932.3046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.61111111111111, "min": 81.53782894736842, "max": 395.4724409448819, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49470.0, "min": 49335.0, "max": 50225.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999920.0, "min": 49911.0, "max": 1999920.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999920.0, "min": 49911.0, "max": 1999920.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4570868015289307, "min": 0.1031496599316597, "max": 2.4723029136657715, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1326.826904296875, "min": 12.996856689453125, "max": 1492.8017578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8403291820376007, "min": 1.7230248411023428, "max": 3.9249969613266695, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2073.7777583003044, "min": 217.1011299788952, "max": 2358.367678105831, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8403291820376007, "min": 1.7230248411023428, "max": 3.9249969613266695, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2073.7777583003044, "min": 217.1011299788952, "max": 2358.367678105831, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01585761022672361, "min": 0.013263367941241692, "max": 0.020206251118603785, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04757283068017083, "min": 0.026526735882483384, "max": 0.05780643008329207, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06452152778704962, "min": 0.021789876371622087, "max": 0.06452152778704962, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19356458336114885, "min": 0.043579752743244174, "max": 0.19356458336114885, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.78469873846666e-06, "min": 3.78469873846666e-06, "max": 0.00029537790154069994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.135409621539998e-05, "min": 1.135409621539998e-05, "max": 0.0008441833686055498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126153333333332, "min": 0.10126153333333332, "max": 0.19845930000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30378459999999996, "min": 0.20765255000000005, "max": 0.5813944499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.295051333333324e-05, "min": 7.295051333333324e-05, "max": 0.004923119069999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002188515399999997, "min": 0.0002188515399999997, "max": 0.014071583055000001, "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": "1679576414", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679578847" }, "total": 2433.091749479, "count": 1, "self": 0.4438078670000323, "children": { "run_training.setup": { "total": 0.11233134799999789, "count": 1, "self": 0.11233134799999789 }, "TrainerController.start_learning": { "total": 2432.5356102640003, "count": 1, "self": 4.275593533009214, "children": { "TrainerController._reset_env": { "total": 9.812481761000015, "count": 1, "self": 9.812481761000015 }, "TrainerController.advance": { "total": 2418.323230326991, "count": 231973, "self": 4.71528054791861, "children": { "env_step": { "total": 1881.9542838640587, "count": 231973, "self": 1590.436903010096, "children": { "SubprocessEnvManager._take_step": { "total": 288.6352280069979, "count": 231973, "self": 17.379661580004836, "children": { "TorchPolicy.evaluate": { "total": 271.2555664269931, "count": 222804, "self": 271.2555664269931 } } }, "workers": { "total": 2.8821528469646296, "count": 231973, "self": 0.0, "children": { "worker_root": { "total": 2424.197525327061, "count": 231973, "is_parallel": true, "self": 1128.8567233310628, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000891920000015034, "count": 1, "is_parallel": true, "self": 0.0002590480000321804, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006328719999828536, "count": 2, "is_parallel": true, "self": 0.0006328719999828536 } } }, "UnityEnvironment.step": { "total": 0.045981496000024435, "count": 1, "is_parallel": true, "self": 0.00036988200002952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021815299999161653, "count": 1, "is_parallel": true, "self": 0.00021815299999161653 }, "communicator.exchange": { "total": 0.04461105799998677, "count": 1, "is_parallel": true, "self": 0.04461105799998677 }, "steps_from_proto": { "total": 0.0007824030000165294, "count": 1, "is_parallel": true, "self": 0.00021118200010050714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005712209999160223, "count": 2, "is_parallel": true, "self": 0.0005712209999160223 } } } } } } }, "UnityEnvironment.step": { "total": 1295.3408019959984, "count": 231972, "is_parallel": true, "self": 39.35765187299694, "children": { "UnityEnvironment._generate_step_input": { "total": 80.25444250700639, "count": 231972, "is_parallel": true, "self": 80.25444250700639 }, "communicator.exchange": { "total": 1084.4314025050485, "count": 231972, "is_parallel": true, "self": 1084.4314025050485 }, "steps_from_proto": { "total": 91.29730511094647, "count": 231972, "is_parallel": true, "self": 34.20866015889328, "children": { "_process_rank_one_or_two_observation": { "total": 57.08864495205319, "count": 463944, "is_parallel": true, "self": 57.08864495205319 } } } } } } } } } } }, "trainer_advance": { "total": 531.6536659150138, "count": 231973, "self": 6.756657894896875, "children": { "process_trajectory": { "total": 145.92935593511913, "count": 231973, "self": 144.48871047311923, "children": { "RLTrainer._checkpoint": { "total": 1.4406454619999067, "count": 10, "self": 1.4406454619999067 } } }, "_update_policy": { "total": 378.9676520849978, "count": 97, "self": 319.3777209959924, "children": { "TorchPPOOptimizer.update": { "total": 59.589931089005404, "count": 2910, "self": 59.589931089005404 } } } } } } }, "trainer_threads": { "total": 1.1124000138806878e-05, "count": 1, "self": 1.1124000138806878e-05 }, "TrainerController._save_models": { "total": 0.12429351899982066, "count": 1, "self": 0.002946955999959755, "children": { "RLTrainer._checkpoint": { "total": 0.12134656299986091, "count": 1, "self": 0.12134656299986091 } } } } } } }