{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4046615362167358, "min": 1.4046615362167358, "max": 1.427144169807434, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69165.53125, "min": 68973.875, "max": 76368.234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.37201907790143, "min": 74.96054628224583, "max": 416.5083333333333, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49296.0, "min": 49094.0, "max": 50075.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999874.0, "min": 49703.0, "max": 1999874.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999874.0, "min": 49703.0, "max": 1999874.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.432060480117798, "min": -0.025813614949584007, "max": 2.4862709045410156, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1529.7659912109375, "min": -3.0718202590942383, "max": 1620.833251953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.814679505525598, "min": 1.6581171440477132, "max": 4.06844557796572, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2399.433408975601, "min": 197.31594014167786, "max": 2648.558071255684, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.814679505525598, "min": 1.6581171440477132, "max": 4.06844557796572, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2399.433408975601, "min": 197.31594014167786, "max": 2648.558071255684, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01586489943890936, "min": 0.013975098980720052, "max": 0.021448746563207048, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04759469831672808, "min": 0.028230004359890398, "max": 0.055458657976244774, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056360440452893575, "min": 0.024052373816569647, "max": 0.06353744218746821, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16908132135868073, "min": 0.048104747633139294, "max": 0.1808664302031199, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.004548665183336e-06, "min": 4.004548665183336e-06, "max": 0.0002953500765499749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.201364599555001e-05, "min": 1.201364599555001e-05, "max": 0.0008443332185555999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10133481666666666, "min": 0.10133481666666666, "max": 0.19845002500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30400445, "min": 0.20779489999999995, "max": 0.5814444, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.660735166666671e-05, "min": 7.660735166666671e-05, "max": 0.004922656247499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022982205500000016, "min": 0.00022982205500000016, "max": 0.01407407556, "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": "1676544312", "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": "1.21.6", "end_time_seconds": "1676546642" }, "total": 2329.2043713800003, "count": 1, "self": 0.5561786260004737, "children": { "run_training.setup": { "total": 0.10810877400001573, "count": 1, "self": 0.10810877400001573 }, "TrainerController.start_learning": { "total": 2328.54008398, "count": 1, "self": 4.063655033009127, "children": { "TrainerController._reset_env": { "total": 9.155350594999959, "count": 1, "self": 9.155350594999959 }, "TrainerController.advance": { "total": 2315.147519288991, "count": 232807, "self": 4.339709451024646, "children": { "env_step": { "total": 1805.4972695928955, "count": 232807, "self": 1503.4427002051434, "children": { "SubprocessEnvManager._take_step": { "total": 299.3822013569488, "count": 232807, "self": 15.274501171925408, "children": { "TorchPolicy.evaluate": { "total": 284.1077001850234, "count": 222868, "self": 70.22271673598084, "children": { "TorchPolicy.sample_actions": { "total": 213.88498344904258, "count": 222868, "self": 213.88498344904258 } } } } }, "workers": { "total": 2.6723680308031135, "count": 232807, "self": 0.0, "children": { "worker_root": { "total": 2320.166927811907, "count": 232807, "is_parallel": true, "self": 1097.361279695927, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018131379999886121, "count": 1, "is_parallel": true, "self": 0.0004309869999588045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013821510000298076, "count": 2, "is_parallel": true, "self": 0.0013821510000298076 } } }, "UnityEnvironment.step": { "total": 0.04211498600000141, "count": 1, "is_parallel": true, "self": 0.0002906969999685316, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002033399999845642, "count": 1, "is_parallel": true, "self": 0.0002033399999845642 }, "communicator.exchange": { "total": 0.04094100300005721, "count": 1, "is_parallel": true, "self": 0.04094100300005721 }, "steps_from_proto": { "total": 0.0006799459999911051, "count": 1, "is_parallel": true, "self": 0.00021014100002503255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004698049999660725, "count": 2, "is_parallel": true, "self": 0.0004698049999660725 } } } } } } }, "UnityEnvironment.step": { "total": 1222.8056481159801, "count": 232806, "is_parallel": true, "self": 37.556724283977246, "children": { "UnityEnvironment._generate_step_input": { "total": 76.35776416297449, "count": 232806, "is_parallel": true, "self": 76.35776416297449 }, "communicator.exchange": { "total": 1005.8349223349674, "count": 232806, "is_parallel": true, "self": 1005.8349223349674 }, "steps_from_proto": { "total": 103.05623733406105, "count": 232806, "is_parallel": true, "self": 36.80036946496591, "children": { "_process_rank_one_or_two_observation": { "total": 66.25586786909514, "count": 465612, "is_parallel": true, "self": 66.25586786909514 } } } } } } } } } } }, "trainer_advance": { "total": 505.310540245071, "count": 232807, "self": 6.672195374094599, "children": { "process_trajectory": { "total": 159.57828991397525, "count": 232807, "self": 158.3475425899736, "children": { "RLTrainer._checkpoint": { "total": 1.2307473240016407, "count": 10, "self": 1.2307473240016407 } } }, "_update_policy": { "total": 339.06005495700117, "count": 97, "self": 282.4464821329967, "children": { "TorchPPOOptimizer.update": { "total": 56.61357282400445, "count": 2910, "self": 56.61357282400445 } } } } } } }, "trainer_threads": { "total": 1.0969997674692422e-06, "count": 1, "self": 1.0969997674692422e-06 }, "TrainerController._save_models": { "total": 0.17355796599986206, "count": 1, "self": 0.002791731999877811, "children": { "RLTrainer._checkpoint": { "total": 0.17076623399998425, "count": 1, "self": 0.17076623399998425 } } } } } } }