{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4088364839553833, "min": 1.4088364839553833, "max": 1.4288266897201538, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69125.96875, "min": 67958.75, "max": 76833.765625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 104.04201680672269, "min": 90.85531135531136, "max": 386.54615384615386, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49524.0, "min": 48960.0, "max": 50251.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49992.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49992.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3234262466430664, "min": 0.0995357409119606, "max": 2.3824241161346436, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1105.950927734375, "min": 12.840110778808594, "max": 1280.3931884765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5949057628627585, "min": 1.7076376492893972, "max": 3.855494010402869, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1711.175143122673, "min": 220.28525675833225, "max": 2030.16558521986, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5949057628627585, "min": 1.7076376492893972, "max": 3.855494010402869, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1711.175143122673, "min": 220.28525675833225, "max": 2030.16558521986, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015666097746482893, "min": 0.013582871308770136, "max": 0.020586256164339525, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.031332195492965786, "min": 0.028695884411475466, "max": 0.0583777700647867, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04581902561088403, "min": 0.022617052764528328, "max": 0.05437094138728247, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09163805122176806, "min": 0.04535687882453203, "max": 0.16311282416184741, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.580873473075005e-06, "min": 4.580873473075005e-06, "max": 0.00029536792654402504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.16174694615001e-06, "min": 9.16174694615001e-06, "max": 0.0008443270685576499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10152692500000005, "min": 0.10152692500000005, "max": 0.198455975, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2030538500000001, "min": 0.2030538500000001, "max": 0.5814423500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.619355750000007e-05, "min": 8.619355750000007e-05, "max": 0.004922953152500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017238711500000014, "min": 0.00017238711500000014, "max": 0.014073973265, "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": "1670438494", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \n[GCC 7.5.0]", "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": "1.21.6", "end_time_seconds": "1670440891" }, "total": 2396.790107292, "count": 1, "self": 0.4002785859997857, "children": { "run_training.setup": { "total": 0.11809149900000193, "count": 1, "self": 0.11809149900000193 }, "TrainerController.start_learning": { "total": 2396.271737207, "count": 1, "self": 4.204856126065351, "children": { "TrainerController._reset_env": { "total": 10.990058719999979, "count": 1, "self": 10.990058719999979 }, "TrainerController.advance": { "total": 2380.950918312935, "count": 231714, "self": 4.4190581728953475, "children": { "env_step": { "total": 1880.0255490469494, "count": 231714, "self": 1584.0090541549546, "children": { "SubprocessEnvManager._take_step": { "total": 293.1739681670408, "count": 231714, "self": 15.361636591057504, "children": { "TorchPolicy.evaluate": { "total": 277.8123315759833, "count": 222892, "self": 69.04148780897322, "children": { "TorchPolicy.sample_actions": { "total": 208.7708437670101, "count": 222892, "self": 208.7708437670101 } } } } }, "workers": { "total": 2.842526724954041, "count": 231714, "self": 0.0, "children": { "worker_root": { "total": 2387.77907865304, "count": 231714, "is_parallel": true, "self": 1085.4469075751028, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007460876999857646, "count": 1, "is_parallel": true, "self": 0.00036429299962037476, "children": { "_process_rank_one_or_two_observation": { "total": 0.0070965840002372715, "count": 2, "is_parallel": true, "self": 0.0070965840002372715 } } }, "UnityEnvironment.step": { "total": 0.02844806600000993, "count": 1, "is_parallel": true, "self": 0.00028992000011385244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002044679999926302, "count": 1, "is_parallel": true, "self": 0.0002044679999926302 }, "communicator.exchange": { "total": 0.02716889899988928, "count": 1, "is_parallel": true, "self": 0.02716889899988928 }, "steps_from_proto": { "total": 0.0007847790000141686, "count": 1, "is_parallel": true, "self": 0.0002602380000098492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005245410000043194, "count": 2, "is_parallel": true, "self": 0.0005245410000043194 } } } } } } }, "UnityEnvironment.step": { "total": 1302.3321710779371, "count": 231713, "is_parallel": true, "self": 36.381728045037335, "children": { "UnityEnvironment._generate_step_input": { "total": 79.04686686896844, "count": 231713, "is_parallel": true, "self": 79.04686686896844 }, "communicator.exchange": { "total": 1089.050730830006, "count": 231713, "is_parallel": true, "self": 1089.050730830006 }, "steps_from_proto": { "total": 97.85284533392542, "count": 231713, "is_parallel": true, "self": 39.46468159792471, "children": { "_process_rank_one_or_two_observation": { "total": 58.388163736000706, "count": 463426, "is_parallel": true, "self": 58.388163736000706 } } } } } } } } } } }, "trainer_advance": { "total": 496.5063110930903, "count": 231714, "self": 6.9528885611148326, "children": { "process_trajectory": { "total": 158.79672647097505, "count": 231714, "self": 158.25347529297483, "children": { "RLTrainer._checkpoint": { "total": 0.5432511780002187, "count": 4, "self": 0.5432511780002187 } } }, "_update_policy": { "total": 330.7566960610004, "count": 96, "self": 275.6255118520005, "children": { "TorchPPOOptimizer.update": { "total": 55.13118420899991, "count": 2880, "self": 55.13118420899991 } } } } } } }, "trainer_threads": { "total": 8.950000847107731e-07, "count": 1, "self": 8.950000847107731e-07 }, "TrainerController._save_models": { "total": 0.12590315299985377, "count": 1, "self": 0.00752140699978554, "children": { "RLTrainer._checkpoint": { "total": 0.11838174600006823, "count": 1, "self": 0.11838174600006823 } } } } } } }