{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 0.6007463335990906, "min": 0.6007463335990906, "max": 0.6007463335990906, "count": 1 }, "Huggy.Policy.Entropy.sum": { "value": 4443.720703125, "min": 4443.720703125, "max": 4443.720703125, "count": 1 }, "Huggy.Environment.EpisodeLength.mean": { "value": 167.78571428571428, "min": 167.78571428571428, "max": 167.78571428571428, "count": 1 }, "Huggy.Environment.EpisodeLength.sum": { "value": 2349.0, "min": 2349.0, "max": 2349.0, "count": 1 }, "Huggy.Step.mean": { "value": 99925.0, "min": 99925.0, "max": 99925.0, "count": 1 }, "Huggy.Step.sum": { "value": 99925.0, "min": 99925.0, "max": 99925.0, "count": 1 }, "Huggy.Policy.ExtrinsicValue.mean": { "value": 355.0265808105469, "min": 355.0265808105469, "max": 355.0265808105469, "count": 1 }, "Huggy.Policy.ExtrinsicValue.sum": { "value": 4615.345703125, "min": 4615.345703125, "max": 4615.345703125, "count": 1 }, "Huggy.Environment.CumulativeReward.mean": { "value": 1.1283439581210797, "min": 1.1283439581210797, "max": 1.1283439581210797, "count": 1 }, "Huggy.Environment.CumulativeReward.sum": { "value": 14.668471455574036, "min": 14.668471455574036, "max": 14.668471455574036, "count": 1 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 1.1283439581210797, "min": 1.1283439581210797, "max": 1.1283439581210797, "count": 1 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 14.668471455574036, "min": 14.668471455574036, "max": 14.668471455574036, "count": 1 }, "Huggy.Losses.PolicyLoss.mean": { "value": -377.51686883773505, "min": -377.51686883773505, "max": -377.51686883773505, "count": 1 }, "Huggy.Losses.PolicyLoss.sum": { "value": -736912.9279712588, "min": -736912.9279712588, "max": -736912.9279712588, "count": 1 }, "Huggy.Losses.ValueLoss.mean": { "value": 37.55478162918095, "min": 37.55478162918095, "max": 37.55478162918095, "count": 1 }, "Huggy.Losses.ValueLoss.sum": { "value": 73306.93374016121, "min": 73306.93374016121, "max": 73306.93374016121, "count": 1 }, "Huggy.Losses.Q1Loss.mean": { "value": 32.88027379275666, "min": 32.88027379275666, "max": 32.88027379275666, "count": 1 }, "Huggy.Losses.Q1Loss.sum": { "value": 64182.294443461, "min": 64182.294443461, "max": 64182.294443461, "count": 1 }, "Huggy.Losses.Q2Loss.mean": { "value": 30.215098221913532, "min": 30.215098221913532, "max": 30.215098221913532, "count": 1 }, "Huggy.Losses.Q2Loss.sum": { "value": 58979.87172917522, "min": 58979.87172917522, "max": 58979.87172917522, "count": 1 }, "Huggy.Policy.ContinuousEntropyCoeff.mean": { "value": 0.6101228481604988, "min": 0.6101228481604988, "max": 0.6101228481604988, "count": 1 }, "Huggy.Policy.ContinuousEntropyCoeff.sum": { "value": 1190.9597996092937, "min": 1190.9597996092937, "max": 1190.9597996092937, "count": 1 }, "Huggy.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "Huggy.Policy.LearningRate.sum": { "value": 0.5855999999999999, "min": 0.5855999999999999, "max": 0.5855999999999999, "count": 1 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1738934928", "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 --resume --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": "1738935067" }, "total": 138.4005149980003, "count": 1, "self": 0.05426449300102831, "children": { "run_training.setup": { "total": 0.020437452999431116, "count": 1, "self": 0.020437452999431116 }, "TrainerController.start_learning": { "total": 138.32581305199983, "count": 1, "self": 0.019194586986486684, "children": { "TrainerController._reset_env": { "total": 2.163946042000134, "count": 1, "self": 2.163946042000134 }, "TrainerController.advance": { "total": 135.7644718560141, "count": 962, "self": 0.016848251021656324, "children": { "env_step": { "total": 8.339853386981304, "count": 962, "self": 6.3132783790006215, "children": { "SubprocessEnvManager._take_step": { "total": 2.0163242189964876, "count": 962, "self": 0.06530384300913283, "children": { "TorchPolicy.evaluate": { "total": 1.9510203759873548, "count": 954, "self": 1.9510203759873548 } } }, "workers": { "total": 0.010250788984194514, "count": 962, "self": 0.0, "children": { "worker_root": { "total": 134.3363206410104, "count": 962, "is_parallel": true, "self": 129.18815153601554, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008550060001653037, "count": 1, "is_parallel": true, "self": 0.0002193910004280042, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006356149997372995, "count": 2, "is_parallel": true, "self": 0.0006356149997372995 } } }, "UnityEnvironment.step": { "total": 0.029458187999807706, "count": 1, "is_parallel": true, "self": 0.00026676699962990824, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001875770003607613, "count": 1, "is_parallel": true, "self": 0.0001875770003607613 }, "communicator.exchange": { "total": 0.028169782000077248, "count": 1, "is_parallel": true, "self": 0.028169782000077248 }, "steps_from_proto": { "total": 0.000834061999739788, "count": 1, "is_parallel": true, "self": 0.0003398689996174653, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004941930001223227, "count": 2, "is_parallel": true, "self": 0.0004941930001223227 } } } } } } }, "UnityEnvironment.step": { "total": 5.1481691049948495, "count": 961, "is_parallel": true, "self": 0.14491284300765983, "children": { "UnityEnvironment._generate_step_input": { "total": 0.332936723979401, "count": 961, "is_parallel": true, "self": 0.332936723979401 }, "communicator.exchange": { "total": 4.328824988002452, "count": 961, "is_parallel": true, "self": 4.328824988002452 }, "steps_from_proto": { "total": 0.34149455000533635, "count": 961, "is_parallel": true, "self": 0.1215183390177117, "children": { "_process_rank_one_or_two_observation": { "total": 0.21997621098762465, "count": 1922, "is_parallel": true, "self": 0.21997621098762465 } } } } } } } } } } }, "trainer_advance": { "total": 127.40777021801114, "count": 962, "self": 0.02621321100559726, "children": { "process_trajectory": { "total": 0.23487424600170925, "count": 962, "self": 0.23487424600170925 }, "_update_policy": { "total": 127.14668276100383, "count": 698, "self": 0.004324537019783747, "children": { "OffPolicyTrainer._update_policy": { "total": 127.14235822398405, "count": 698, "self": 54.006551052007126, "children": { "TorchSACOptimizer.update": { "total": 73.13580717197692, "count": 3639, "self": 73.13580717197692 } } } } } } } } }, "trainer_threads": { "total": 1.6889998732949607e-06, "count": 1, "self": 1.6889998732949607e-06 }, "TrainerController._save_models": { "total": 0.3781988779992389, "count": 1, "self": 0.005318793999322224, "children": { "RLTrainer._checkpoint": { "total": 0.3728800839999167, "count": 1, "self": 0.3728800839999167 } } } } } } }