{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403069257736206, "min": 1.403069257736206, "max": 1.4298046827316284, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71149.640625, "min": 68138.8828125, "max": 77713.421875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.1794425087108, "min": 84.94168096054888, "max": 400.056, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49467.0, "min": 48866.0, "max": 50026.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999985.0, "min": 49776.0, "max": 1999985.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999985.0, "min": 49776.0, "max": 1999985.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4232468605041504, "min": 0.0492953322827816, "max": 2.4718427658081055, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1390.9437255859375, "min": 6.112621307373047, "max": 1398.687255859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.759560770585562, "min": 1.7277066527355103, "max": 3.9015451093726123, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2157.9878823161125, "min": 214.23562493920326, "max": 2200.4714416861534, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.759560770585562, "min": 1.7277066527355103, "max": 3.9015451093726123, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2157.9878823161125, "min": 214.23562493920326, "max": 2200.4714416861534, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015038461095213682, "min": 0.013656080609265094, "max": 0.019821339562380066, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04511538328564105, "min": 0.02731216121853019, "max": 0.05600776835926808, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0638710141595867, "min": 0.02236103021229307, "max": 0.0638710141595867, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19161304247876007, "min": 0.04472206042458614, "max": 0.19161304247876007, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.217648927483336e-06, "min": 3.217648927483336e-06, "max": 0.00029529150156949995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.652946782450008e-06, "min": 9.652946782450008e-06, "max": 0.0008440339686553499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107251666666668, "min": 0.10107251666666668, "max": 0.19843050000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30321755000000006, "min": 0.20727875, "max": 0.58134465, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.35185816666667e-05, "min": 6.35185816666667e-05, "max": 0.004921681950000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019055574500000008, "min": 0.00019055574500000008, "max": 0.014069098035, "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": "1673192698", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \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": "1673194846" }, "total": 2147.935008712, "count": 1, "self": 0.3897218510001039, "children": { "run_training.setup": { "total": 0.10718716899998526, "count": 1, "self": 0.10718716899998526 }, "TrainerController.start_learning": { "total": 2147.438099692, "count": 1, "self": 3.6167685339823947, "children": { "TrainerController._reset_env": { "total": 8.473504527000046, "count": 1, "self": 8.473504527000046 }, "TrainerController.advance": { "total": 2135.2324167330175, "count": 231987, "self": 3.7832695569136376, "children": { "env_step": { "total": 1678.3836468460381, "count": 231987, "self": 1413.2249370630261, "children": { "SubprocessEnvManager._take_step": { "total": 262.721565008055, "count": 231987, "self": 13.55091418093457, "children": { "TorchPolicy.evaluate": { "total": 249.17065082712043, "count": 223008, "self": 62.52308384908531, "children": { "TorchPolicy.sample_actions": { "total": 186.64756697803512, "count": 223008, "self": 186.64756697803512 } } } } }, "workers": { "total": 2.437144774957119, "count": 231987, "self": 0.0, "children": { "worker_root": { "total": 2139.920258323063, "count": 231987, "is_parallel": true, "self": 975.1254327660247, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002432790000057139, "count": 1, "is_parallel": true, "self": 0.00034717500011538505, "children": { "_process_rank_one_or_two_observation": { "total": 0.002085614999941754, "count": 2, "is_parallel": true, "self": 0.002085614999941754 } } }, "UnityEnvironment.step": { "total": 0.027195098999982292, "count": 1, "is_parallel": true, "self": 0.00028512100004718377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017259599997032637, "count": 1, "is_parallel": true, "self": 0.00017259599997032637 }, "communicator.exchange": { "total": 0.0260209880000275, "count": 1, "is_parallel": true, "self": 0.0260209880000275 }, "steps_from_proto": { "total": 0.0007163939999372815, "count": 1, "is_parallel": true, "self": 0.0002354879999302284, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004809060000070531, "count": 2, "is_parallel": true, "self": 0.0004809060000070531 } } } } } } }, "UnityEnvironment.step": { "total": 1164.7948255570384, "count": 231986, "is_parallel": true, "self": 33.7580920360017, "children": { "UnityEnvironment._generate_step_input": { "total": 74.85369392308314, "count": 231986, "is_parallel": true, "self": 74.85369392308314 }, "communicator.exchange": { "total": 964.5595393909435, "count": 231986, "is_parallel": true, "self": 964.5595393909435 }, "steps_from_proto": { "total": 91.62350020701001, "count": 231986, "is_parallel": true, "self": 37.570323990957604, "children": { "_process_rank_one_or_two_observation": { "total": 54.05317621605241, "count": 463972, "is_parallel": true, "self": 54.05317621605241 } } } } } } } } } } }, "trainer_advance": { "total": 453.06550033006556, "count": 231987, "self": 5.683320064021586, "children": { "process_trajectory": { "total": 142.43971130604598, "count": 231987, "self": 141.27044113404713, "children": { "RLTrainer._checkpoint": { "total": 1.1692701719988463, "count": 10, "self": 1.1692701719988463 } } }, "_update_policy": { "total": 304.942468959998, "count": 97, "self": 252.11383328100442, "children": { "TorchPPOOptimizer.update": { "total": 52.82863567899358, "count": 2910, "self": 52.82863567899358 } } } } } } }, "trainer_threads": { "total": 8.990000424091704e-07, "count": 1, "self": 8.990000424091704e-07 }, "TrainerController._save_models": { "total": 0.11540899900001023, "count": 1, "self": 0.002106365999679838, "children": { "RLTrainer._checkpoint": { "total": 0.11330263300033039, "count": 1, "self": 0.11330263300033039 } } } } } } }