{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4079737663269043, "min": 1.4079737663269043, "max": 1.4291695356369019, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71227.984375, "min": 68628.1953125, "max": 75078.640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.96641791044776, "min": 82.87913907284768, "max": 398.6904761904762, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48758.0, "min": 48758.0, "max": 50235.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999998.0, "min": 49787.0, "max": 1999998.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999998.0, "min": 49787.0, "max": 1999998.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5182619094848633, "min": -0.07625475525856018, "max": 2.5182619094848633, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1349.788330078125, "min": -9.531844139099121, "max": 1490.6578369140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9431023364191624, "min": 1.793380956172943, "max": 3.9431023364191624, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2113.502852320671, "min": 224.1726195216179, "max": 2261.6308418512344, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9431023364191624, "min": 1.793380956172943, "max": 3.9431023364191624, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2113.502852320671, "min": 224.1726195216179, "max": 2261.6308418512344, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01787679755264738, "min": 0.0126404040829382, "max": 0.020526619379006662, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05363039265794214, "min": 0.028640809658099897, "max": 0.05631360721624029, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05718075380557114, "min": 0.022731745957086484, "max": 0.06247149650007486, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17154226141671342, "min": 0.04546349191417297, "max": 0.1854217557857434, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4668988444000027e-06, "min": 3.4668988444000027e-06, "max": 0.00029534640155119994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0400696533200008e-05, "min": 1.0400696533200008e-05, "max": 0.0008443341185553, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011556, "min": 0.1011556, "max": 0.19844880000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034668, "min": 0.20744455, "max": 0.5814447000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.766444000000005e-05, "min": 6.766444000000005e-05, "max": 0.00492259512, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020299332000000016, "min": 0.00020299332000000016, "max": 0.014074090530000001, "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": "1677310109", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677312793" }, "total": 2683.379071825, "count": 1, "self": 0.4428426419999596, "children": { "run_training.setup": { "total": 0.20671971000001577, "count": 1, "self": 0.20671971000001577 }, "TrainerController.start_learning": { "total": 2682.7295094730002, "count": 1, "self": 5.097406608039819, "children": { "TrainerController._reset_env": { "total": 10.810607328999993, "count": 1, "self": 10.810607328999993 }, "TrainerController.advance": { "total": 2666.7026593059604, "count": 232143, "self": 5.531726000981507, "children": { "env_step": { "total": 2058.1534556680367, "count": 232143, "self": 1721.5733177729683, "children": { "SubprocessEnvManager._take_step": { "total": 333.3310088380303, "count": 232143, "self": 18.120220990070663, "children": { "TorchPolicy.evaluate": { "total": 315.21078784795964, "count": 223069, "self": 81.15658724990834, "children": { "TorchPolicy.sample_actions": { "total": 234.0542005980513, "count": 223069, "self": 234.0542005980513 } } } } }, "workers": { "total": 3.2491290570381466, "count": 232143, "self": 0.0, "children": { "worker_root": { "total": 2672.7883869819702, "count": 232143, "is_parallel": true, "self": 1281.2569945078833, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003389356000013777, "count": 1, "is_parallel": true, "self": 0.0004057699999862052, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029835860000275716, "count": 2, "is_parallel": true, "self": 0.0029835860000275716 } } }, "UnityEnvironment.step": { "total": 0.05865716300002077, "count": 1, "is_parallel": true, "self": 0.0003515760000141199, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042511899999908564, "count": 1, "is_parallel": true, "self": 0.00042511899999908564 }, "communicator.exchange": { "total": 0.0571107819999952, "count": 1, "is_parallel": true, "self": 0.0571107819999952 }, "steps_from_proto": { "total": 0.0007696860000123706, "count": 1, "is_parallel": true, "self": 0.0002428290000011657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005268570000112049, "count": 2, "is_parallel": true, "self": 0.0005268570000112049 } } } } } } }, "UnityEnvironment.step": { "total": 1391.531392474087, "count": 232142, "is_parallel": true, "self": 42.86064453011477, "children": { "UnityEnvironment._generate_step_input": { "total": 82.80501603999562, "count": 232142, "is_parallel": true, "self": 82.80501603999562 }, "communicator.exchange": { "total": 1165.302377514875, "count": 232142, "is_parallel": true, "self": 1165.302377514875 }, "steps_from_proto": { "total": 100.5633543891015, "count": 232142, "is_parallel": true, "self": 40.02683730501582, "children": { "_process_rank_one_or_two_observation": { "total": 60.53651708408569, "count": 464284, "is_parallel": true, "self": 60.53651708408569 } } } } } } } } } } }, "trainer_advance": { "total": 603.0174776369421, "count": 232143, "self": 7.892983906912491, "children": { "process_trajectory": { "total": 170.39926730102957, "count": 232143, "self": 169.15655125202886, "children": { "RLTrainer._checkpoint": { "total": 1.2427160490007054, "count": 10, "self": 1.2427160490007054 } } }, "_update_policy": { "total": 424.7252264290001, "count": 97, "self": 361.50816077199045, "children": { "TorchPPOOptimizer.update": { "total": 63.21706565700964, "count": 2910, "self": 63.21706565700964 } } } } } } }, "trainer_threads": { "total": 8.990000424091704e-07, "count": 1, "self": 8.990000424091704e-07 }, "TrainerController._save_models": { "total": 0.11883533099990018, "count": 1, "self": 0.0024454019999211596, "children": { "RLTrainer._checkpoint": { "total": 0.11638992899997902, "count": 1, "self": 0.11638992899997902 } } } } } } }