{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4077966213226318, "min": 1.4077966213226318, "max": 1.4262317419052124, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70751.6328125, "min": 69411.84375, "max": 76462.109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.12457912457913, "min": 80.17045454545455, "max": 395.8976377952756, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49376.0, "min": 48807.0, "max": 50279.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999907.0, "min": 49717.0, "max": 1999907.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999907.0, "min": 49717.0, "max": 1999907.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3799896240234375, "min": 0.11928926408290863, "max": 2.477186441421509, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1413.7138671875, "min": 15.030447006225586, "max": 1474.3717041015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6711471302541416, "min": 1.7923264820424338, "max": 3.9926051719337954, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2180.6613953709602, "min": 225.83313673734665, "max": 2359.629656612873, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6711471302541416, "min": 1.7923264820424338, "max": 3.9926051719337954, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2180.6613953709602, "min": 225.83313673734665, "max": 2359.629656612873, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016905959546501335, "min": 0.013701842130588678, "max": 0.022379316916340028, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050717878639504006, "min": 0.027403684261177355, "max": 0.05606260688315767, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05285606020026737, "min": 0.022383574365327757, "max": 0.06038239089151223, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1585681806008021, "min": 0.044767148730655515, "max": 0.17115158811211587, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6771487743166595e-06, "min": 3.6771487743166595e-06, "max": 0.00029534730155089987, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1031446322949978e-05, "min": 1.1031446322949978e-05, "max": 0.0008437366687544497, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122568333333333, "min": 0.10122568333333333, "max": 0.1984491, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30367705, "min": 0.20767259999999998, "max": 0.5812455500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.11615983333332e-05, "min": 7.11615983333332e-05, "max": 0.00492261009, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021348479499999962, "min": 0.00021348479499999962, "max": 0.014064152945, "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": "1701894969", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701897433" }, "total": 2463.264304704, "count": 1, "self": 0.44378140300023006, "children": { "run_training.setup": { "total": 0.09350497200011887, "count": 1, "self": 0.09350497200011887 }, "TrainerController.start_learning": { "total": 2462.7270183289997, "count": 1, "self": 4.388504734114122, "children": { "TrainerController._reset_env": { "total": 4.154957165999804, "count": 1, "self": 4.154957165999804 }, "TrainerController.advance": { "total": 2454.061264619886, "count": 232500, "self": 4.719639452914635, "children": { "env_step": { "total": 1963.6260880989598, "count": 232500, "self": 1617.2026225312225, "children": { "SubprocessEnvManager._take_step": { "total": 343.62221075971684, "count": 232500, "self": 16.865350956554266, "children": { "TorchPolicy.evaluate": { "total": 326.75685980316257, "count": 222967, "self": 326.75685980316257 } } }, "workers": { "total": 2.8012548080205306, "count": 232500, "self": 0.0, "children": { "worker_root": { "total": 2455.25516479803, "count": 232500, "is_parallel": true, "self": 1142.4634703368724, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011290679999547137, "count": 1, "is_parallel": true, "self": 0.00034140200023102807, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007876659997236857, "count": 2, "is_parallel": true, "self": 0.0007876659997236857 } } }, "UnityEnvironment.step": { "total": 0.029537929000071017, "count": 1, "is_parallel": true, "self": 0.0003039269995497307, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020833799999309122, "count": 1, "is_parallel": true, "self": 0.00020833799999309122 }, "communicator.exchange": { "total": 0.02831733000039094, "count": 1, "is_parallel": true, "self": 0.02831733000039094 }, "steps_from_proto": { "total": 0.0007083340001372562, "count": 1, "is_parallel": true, "self": 0.0002027049999924202, "children": { "_process_rank_one_or_two_observation": { "total": 0.000505629000144836, "count": 2, "is_parallel": true, "self": 0.000505629000144836 } } } } } } }, "UnityEnvironment.step": { "total": 1312.7916944611575, "count": 232499, "is_parallel": true, "self": 40.134605835470666, "children": { "UnityEnvironment._generate_step_input": { "total": 87.8537366169453, "count": 232499, "is_parallel": true, "self": 87.8537366169453 }, "communicator.exchange": { "total": 1091.4389993969817, "count": 232499, "is_parallel": true, "self": 1091.4389993969817 }, "steps_from_proto": { "total": 93.36435261175984, "count": 232499, "is_parallel": true, "self": 35.25712228696557, "children": { "_process_rank_one_or_two_observation": { "total": 58.10723032479427, "count": 464998, "is_parallel": true, "self": 58.10723032479427 } } } } } } } } } } }, "trainer_advance": { "total": 485.7155370680116, "count": 232500, "self": 6.673394642110452, "children": { "process_trajectory": { "total": 156.86710570690684, "count": 232500, "self": 155.49398795190655, "children": { "RLTrainer._checkpoint": { "total": 1.373117755000294, "count": 10, "self": 1.373117755000294 } } }, "_update_policy": { "total": 322.1750367189943, "count": 97, "self": 270.036769256998, "children": { "TorchPPOOptimizer.update": { "total": 52.13826746199629, "count": 2910, "self": 52.13826746199629 } } } } } } }, "trainer_threads": { "total": 1.008999788609799e-06, "count": 1, "self": 1.008999788609799e-06 }, "TrainerController._save_models": { "total": 0.12229079999997339, "count": 1, "self": 0.0019738569999390165, "children": { "RLTrainer._checkpoint": { "total": 0.12031694300003437, "count": 1, "self": 0.12031694300003437 } } } } } } }