{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403747797012329, "min": 1.403747797012329, "max": 1.428682565689087, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68377.9609375, "min": 68377.9609375, "max": 77491.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 79.59032258064516, "min": 69.0013986013986, "max": 400.568, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49346.0, "min": 49178.0, "max": 50071.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999915.0, "min": 49849.0, "max": 1999915.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999915.0, "min": 49849.0, "max": 1999915.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.452906847000122, "min": 0.09449683874845505, "max": 2.56415057182312, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1520.80224609375, "min": 11.717608451843262, "max": 1761.170166015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7561427861452104, "min": 1.7071929501910363, "max": 4.055413291076761, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2328.8085274100304, "min": 211.6919258236885, "max": 2770.19799888134, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7561427861452104, "min": 1.7071929501910363, "max": 4.055413291076761, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2328.8085274100304, "min": 211.6919258236885, "max": 2770.19799888134, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01355712976065762, "min": 0.01355712976065762, "max": 0.0191361604977121, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04067138928197286, "min": 0.02860584242832071, "max": 0.0574084814931363, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05360094259182612, "min": 0.021782644900182883, "max": 0.060680550833543144, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16080282777547836, "min": 0.04356528980036577, "max": 0.17387855648994444, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.779348740250013e-06, "min": 3.779348740250013e-06, "max": 0.00029533867655377494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1338046220750038e-05, "min": 1.1338046220750038e-05, "max": 0.00084427396857535, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125975, "min": 0.10125975, "max": 0.198446225, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30377925, "min": 0.20765480000000006, "max": 0.58142465, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.286152500000021e-05, "min": 7.286152500000021e-05, "max": 0.004922466627500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021858457500000062, "min": 0.00021858457500000062, "max": 0.014073090035000001, "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": "1740562870", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740565358" }, "total": 2487.69487519, "count": 1, "self": 0.4374910199999249, "children": { "run_training.setup": { "total": 0.022877945999994154, "count": 1, "self": 0.022877945999994154 }, "TrainerController.start_learning": { "total": 2487.234506224, "count": 1, "self": 4.522452727104792, "children": { "TrainerController._reset_env": { "total": 2.876274370000033, "count": 1, "self": 2.876274370000033 }, "TrainerController.advance": { "total": 2479.7170335658952, "count": 233458, "self": 4.766873328882866, "children": { "env_step": { "total": 1984.4477967150444, "count": 233458, "self": 1554.5380759751806, "children": { "SubprocessEnvManager._take_step": { "total": 427.209927297946, "count": 233458, "self": 15.798232839901402, "children": { "TorchPolicy.evaluate": { "total": 411.4116944580446, "count": 222897, "self": 411.4116944580446 } } }, "workers": { "total": 2.699793441917791, "count": 233458, "self": 0.0, "children": { "worker_root": { "total": 2479.8807509949, "count": 233458, "is_parallel": true, "self": 1213.4109909558542, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001148931999978231, "count": 1, "is_parallel": true, "self": 0.0003865720001385853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007623599998396458, "count": 2, "is_parallel": true, "self": 0.0007623599998396458 } } }, "UnityEnvironment.step": { "total": 0.02974997599994822, "count": 1, "is_parallel": true, "self": 0.0003025919999117832, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018563399999038666, "count": 1, "is_parallel": true, "self": 0.00018563399999038666 }, "communicator.exchange": { "total": 0.02857234200007497, "count": 1, "is_parallel": true, "self": 0.02857234200007497 }, "steps_from_proto": { "total": 0.0006894079999710812, "count": 1, "is_parallel": true, "self": 0.0002168109999729495, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047259699999813165, "count": 2, "is_parallel": true, "self": 0.00047259699999813165 } } } } } } }, "UnityEnvironment.step": { "total": 1266.469760039046, "count": 233457, "is_parallel": true, "self": 37.70052698987911, "children": { "UnityEnvironment._generate_step_input": { "total": 83.35184171707226, "count": 233457, "is_parallel": true, "self": 83.35184171707226 }, "communicator.exchange": { "total": 1056.2987670819734, "count": 233457, "is_parallel": true, "self": 1056.2987670819734 }, "steps_from_proto": { "total": 89.11862425012123, "count": 233457, "is_parallel": true, "self": 33.490061004268455, "children": { "_process_rank_one_or_two_observation": { "total": 55.628563245852774, "count": 466914, "is_parallel": true, "self": 55.628563245852774 } } } } } } } } } } }, "trainer_advance": { "total": 490.50236352196805, "count": 233458, "self": 6.6977445829655835, "children": { "process_trajectory": { "total": 172.8328825690022, "count": 233458, "self": 171.45929092400308, "children": { "RLTrainer._checkpoint": { "total": 1.3735916449991237, "count": 10, "self": 1.3735916449991237 } } }, "_update_policy": { "total": 310.97173637000026, "count": 97, "self": 247.1928761759957, "children": { "TorchPPOOptimizer.update": { "total": 63.77886019400455, "count": 2910, "self": 63.77886019400455 } } } } } } }, "trainer_threads": { "total": 1.6880003386177123e-06, "count": 1, "self": 1.6880003386177123e-06 }, "TrainerController._save_models": { "total": 0.11874387299985756, "count": 1, "self": 0.0018781080002554518, "children": { "RLTrainer._checkpoint": { "total": 0.1168657649996021, "count": 1, "self": 0.1168657649996021 } } } } } } }