{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4051117897033691, "min": 1.4051117897033691, "max": 1.429174780845642, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70868.21875, "min": 67893.515625, "max": 77214.734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 122.00496277915633, "min": 101.68518518518519, "max": 435.2086956521739, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49168.0, "min": 48981.0, "max": 50350.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999536.0, "min": 49477.0, "max": 1999536.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999536.0, "min": 49477.0, "max": 1999536.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.29941463470459, "min": 0.06718219816684723, "max": 2.379878282546997, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 926.6640625, "min": 7.658770561218262, "max": 1133.51708984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5068947763064364, "min": 1.9440466803416871, "max": 3.8347462564706802, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1413.2785948514938, "min": 221.62132155895233, "max": 1710.4028007388115, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5068947763064364, "min": 1.9440466803416871, "max": 3.8347462564706802, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1413.2785948514938, "min": 221.62132155895233, "max": 1710.4028007388115, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016993636454248593, "min": 0.013419511977958286, "max": 0.019247356598013236, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05098090936274578, "min": 0.026896895280030246, "max": 0.05687940339242535, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04409962478611205, "min": 0.022889673120031755, "max": 0.06069572145740191, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13229887435833615, "min": 0.04577934624006351, "max": 0.16575602777302265, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2618989127333255e-06, "min": 3.2618989127333255e-06, "max": 0.0002953579515473499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.785696738199977e-06, "min": 9.785696738199977e-06, "max": 0.0008440977186341, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108726666666663, "min": 0.10108726666666663, "max": 0.19845265000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032617999999999, "min": 0.20730180000000004, "max": 0.5813659, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.425460666666655e-05, "min": 6.425460666666655e-05, "max": 0.004922787235, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019276381999999966, "min": 0.00019276381999999966, "max": 0.01407015841, "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": "1671984434", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671986701" }, "total": 2266.6311234610002, "count": 1, "self": 0.38919860900023195, "children": { "run_training.setup": { "total": 0.11253593300034481, "count": 1, "self": 0.11253593300034481 }, "TrainerController.start_learning": { "total": 2266.1293889189997, "count": 1, "self": 3.871102323890682, "children": { "TrainerController._reset_env": { "total": 7.245321189999686, "count": 1, "self": 7.245321189999686 }, "TrainerController.advance": { "total": 2254.898298627109, "count": 230754, "self": 4.045946738337989, "children": { "env_step": { "total": 1787.3356595578862, "count": 230754, "self": 1495.1846741406548, "children": { "SubprocessEnvManager._take_step": { "total": 289.50303254723394, "count": 230754, "self": 14.59273681641207, "children": { "TorchPolicy.evaluate": { "total": 274.9102957308219, "count": 223083, "self": 69.02752846797557, "children": { "TorchPolicy.sample_actions": { "total": 205.8827672628463, "count": 223083, "self": 205.8827672628463 } } } } }, "workers": { "total": 2.6479528699974253, "count": 230754, "self": 0.0, "children": { "worker_root": { "total": 2258.2416523389556, "count": 230754, "is_parallel": true, "self": 1031.7770675418783, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017736459999468934, "count": 1, "is_parallel": true, "self": 0.0003384949995961506, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014351510003507428, "count": 2, "is_parallel": true, "self": 0.0014351510003507428 } } }, "UnityEnvironment.step": { "total": 0.03023527400000603, "count": 1, "is_parallel": true, "self": 0.00027826199993796763, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018047399998977198, "count": 1, "is_parallel": true, "self": 0.00018047399998977198 }, "communicator.exchange": { "total": 0.02907417300002635, "count": 1, "is_parallel": true, "self": 0.02907417300002635 }, "steps_from_proto": { "total": 0.000702365000051941, "count": 1, "is_parallel": true, "self": 0.0002324170000065351, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046994800004540593, "count": 2, "is_parallel": true, "self": 0.00046994800004540593 } } } } } } }, "UnityEnvironment.step": { "total": 1226.4645847970774, "count": 230753, "is_parallel": true, "self": 34.910059644080775, "children": { "UnityEnvironment._generate_step_input": { "total": 80.9509562639596, "count": 230753, "is_parallel": true, "self": 80.9509562639596 }, "communicator.exchange": { "total": 1015.1120094879584, "count": 230753, "is_parallel": true, "self": 1015.1120094879584 }, "steps_from_proto": { "total": 95.49155940107858, "count": 230753, "is_parallel": true, "self": 41.503314095765745, "children": { "_process_rank_one_or_two_observation": { "total": 53.98824530531283, "count": 461506, "is_parallel": true, "self": 53.98824530531283 } } } } } } } } } } }, "trainer_advance": { "total": 463.5166923308848, "count": 230754, "self": 6.143675828133382, "children": { "process_trajectory": { "total": 142.64098545474917, "count": 230754, "self": 141.47957682074912, "children": { "RLTrainer._checkpoint": { "total": 1.161408634000054, "count": 10, "self": 1.161408634000054 } } }, "_update_policy": { "total": 314.7320310480022, "count": 97, "self": 262.2284094870047, "children": { "TorchPPOOptimizer.update": { "total": 52.503621560997544, "count": 2910, "self": 52.503621560997544 } } } } } } }, "trainer_threads": { "total": 8.180004442692734e-07, "count": 1, "self": 8.180004442692734e-07 }, "TrainerController._save_models": { "total": 0.11466595999991114, "count": 1, "self": 0.0018757629995889147, "children": { "RLTrainer._checkpoint": { "total": 0.11279019700032222, "count": 1, "self": 0.11279019700032222 } } } } } } }