{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054036140441895, "min": 1.4054036140441895, "max": 1.4267886877059937, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70427.5859375, "min": 69257.0859375, "max": 76782.0234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.1943887775551, "min": 78.54054054054055, "max": 389.953125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49498.0, "min": 49074.0, "max": 50027.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999981.0, "min": 49549.0, "max": 1999981.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999981.0, "min": 49549.0, "max": 1999981.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4487411975860596, "min": 0.06888269633054733, "max": 2.4732508659362793, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1221.921875, "min": 8.748102188110352, "max": 1513.0076904296875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7098055982398606, "min": 1.7697006963838742, "max": 3.9980425455162343, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1851.1929935216904, "min": 224.75198844075203, "max": 2390.740195453167, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7098055982398606, "min": 1.7697006963838742, "max": 3.9980425455162343, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1851.1929935216904, "min": 224.75198844075203, "max": 2390.740195453167, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01789646370097115, "min": 0.012959905847674237, "max": 0.02155887595860501, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05368939110291345, "min": 0.025919811695348474, "max": 0.05473516043954684, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04716665334999561, "min": 0.02245938979710142, "max": 0.06410749697436889, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14149996004998683, "min": 0.04491877959420284, "max": 0.18402502425014972, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5229488257166663e-06, "min": 3.5229488257166663e-06, "max": 0.00029536155154614996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0568846477149999e-05, "min": 1.0568846477149999e-05, "max": 0.0008440533186488998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117428333333335, "min": 0.10117428333333335, "max": 0.19845385000000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30352285000000007, "min": 0.20754800000000004, "max": 0.5813511, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.859673833333332e-05, "min": 6.859673833333332e-05, "max": 0.004922847115, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020579021499999995, "min": 0.00020579021499999995, "max": 0.014069419890000002, "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": "1780163067", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1780165796" }, "total": 2728.128653977, "count": 1, "self": 0.44051637400025356, "children": { "run_training.setup": { "total": 0.050433245999556675, "count": 1, "self": 0.050433245999556675 }, "TrainerController.start_learning": { "total": 2727.637704357, "count": 1, "self": 4.501952444782546, "children": { "TrainerController._reset_env": { "total": 2.869263730000057, "count": 1, "self": 2.869263730000057 }, "TrainerController.advance": { "total": 2720.1575010342167, "count": 232726, "self": 4.744761066162937, "children": { "env_step": { "total": 2240.5618878590267, "count": 232726, "self": 1802.122420284034, "children": { "SubprocessEnvManager._take_step": { "total": 435.60987552988536, "count": 232726, "self": 16.463347348000752, "children": { "TorchPolicy.evaluate": { "total": 419.1465281818846, "count": 223104, "self": 419.1465281818846 } } }, "workers": { "total": 2.829592045107347, "count": 232726, "self": 0.0, "children": { "worker_root": { "total": 2714.50162806781, "count": 232726, "is_parallel": true, "self": 1261.159509390739, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008138670000334969, "count": 1, "is_parallel": true, "self": 0.0002351200009798049, "children": { "_process_rank_one_or_two_observation": { "total": 0.000578746999053692, "count": 2, "is_parallel": true, "self": 0.000578746999053692 } } }, "UnityEnvironment.step": { "total": 0.03352855599950999, "count": 1, "is_parallel": true, "self": 0.00028435600052034715, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002206070003012428, "count": 1, "is_parallel": true, "self": 0.0002206070003012428 }, "communicator.exchange": { "total": 0.03225581299921032, "count": 1, "is_parallel": true, "self": 0.03225581299921032 }, "steps_from_proto": { "total": 0.0007677799994780798, "count": 1, "is_parallel": true, "self": 0.00018520699995860923, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005825729995194706, "count": 2, "is_parallel": true, "self": 0.0005825729995194706 } } } } } } }, "UnityEnvironment.step": { "total": 1453.342118677071, "count": 232725, "is_parallel": true, "self": 39.28969768405477, "children": { "UnityEnvironment._generate_step_input": { "total": 89.59989881811089, "count": 232725, "is_parallel": true, "self": 89.59989881811089 }, "communicator.exchange": { "total": 1230.0216801379447, "count": 232725, "is_parallel": true, "self": 1230.0216801379447 }, "steps_from_proto": { "total": 94.43084203696071, "count": 232725, "is_parallel": true, "self": 34.23057429077198, "children": { "_process_rank_one_or_two_observation": { "total": 60.20026774618873, "count": 465450, "is_parallel": true, "self": 60.20026774618873 } } } } } } } } } } }, "trainer_advance": { "total": 474.8508521090271, "count": 232726, "self": 6.60957204391616, "children": { "process_trajectory": { "total": 162.91846787911527, "count": 232726, "self": 161.7760139081165, "children": { "RLTrainer._checkpoint": { "total": 1.1424539709987585, "count": 10, "self": 1.1424539709987585 } } }, "_update_policy": { "total": 305.32281218599564, "count": 97, "self": 242.61427354097032, "children": { "TorchPPOOptimizer.update": { "total": 62.70853864502533, "count": 2910, "self": 62.70853864502533 } } } } } } }, "trainer_threads": { "total": 1.3050002962700091e-06, "count": 1, "self": 1.3050002962700091e-06 }, "TrainerController._save_models": { "total": 0.10898584300048242, "count": 1, "self": 0.001615657000002102, "children": { "RLTrainer._checkpoint": { "total": 0.10737018600048032, "count": 1, "self": 0.10737018600048032 } } } } } } }