{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405651569366455, "min": 1.405651569366455, "max": 1.4265307188034058, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71147.0546875, "min": 68244.5859375, "max": 78337.2265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.78456014362656, "min": 88.78456014362656, "max": 389.48062015503876, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49453.0, "min": 48869.0, "max": 50243.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999925.0, "min": 49720.0, "max": 1999925.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999925.0, "min": 49720.0, "max": 1999925.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3665900230407715, "min": 0.01615036278963089, "max": 2.427845001220703, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1318.190673828125, "min": 2.067246437072754, "max": 1318.190673828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6632659712428466, "min": 1.7063825273653492, "max": 3.7978423082508805, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2040.4391459822655, "min": 218.4169635027647, "max": 2040.4391459822655, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6632659712428466, "min": 1.7063825273653492, "max": 3.7978423082508805, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2040.4391459822655, "min": 218.4169635027647, "max": 2040.4391459822655, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014705885915706556, "min": 0.013440026093545991, "max": 0.019038749972403617, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.02941177183141311, "min": 0.026880052187091982, "max": 0.05711624991721085, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05202161855995655, "min": 0.022894639242440465, "max": 0.06871160926918189, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1040432371199131, "min": 0.04578927848488093, "max": 0.19097600169479845, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.528523490524996e-06, "min": 4.528523490524996e-06, "max": 0.00029527590157469994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.057046981049993e-06, "min": 9.057046981049993e-06, "max": 0.0008437944187351999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10150947499999996, "min": 0.10150947499999996, "max": 0.19842529999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20301894999999992, "min": 0.20301894999999992, "max": 0.5812648, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.532280249999994e-05, "min": 8.532280249999994e-05, "max": 0.00492142247, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001706456049999999, "min": 0.0001706456049999999, "max": 0.01406511352, "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": "1670861490", "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": "1670863644" }, "total": 2153.923043034, "count": 1, "self": 0.3899735210002291, "children": { "run_training.setup": { "total": 0.1069794790000742, "count": 1, "self": 0.1069794790000742 }, "TrainerController.start_learning": { "total": 2153.4260900339996, "count": 1, "self": 3.7048133019311535, "children": { "TrainerController._reset_env": { "total": 11.208578579000005, "count": 1, "self": 11.208578579000005 }, "TrainerController.advance": { "total": 2138.404176518068, "count": 231322, "self": 4.010063808010273, "children": { "env_step": { "total": 1680.58411943509, "count": 231322, "self": 1413.2548568350758, "children": { "SubprocessEnvManager._take_step": { "total": 264.811525737922, "count": 231322, "self": 13.85309673191864, "children": { "TorchPolicy.evaluate": { "total": 250.95842900600337, "count": 222910, "self": 63.527597162866186, "children": { "TorchPolicy.sample_actions": { "total": 187.43083184313718, "count": 222910, "self": 187.43083184313718 } } } } }, "workers": { "total": 2.517736862092306, "count": 231322, "self": 0.0, "children": { "worker_root": { "total": 2145.525042555109, "count": 231322, "is_parallel": true, "self": 982.8763971502126, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020058969998899556, "count": 1, "is_parallel": true, "self": 0.00029291000009834534, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017129869997916103, "count": 2, "is_parallel": true, "self": 0.0017129869997916103 } } }, "UnityEnvironment.step": { "total": 0.027173313000048438, "count": 1, "is_parallel": true, "self": 0.00026347600010012684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020456299989746185, "count": 1, "is_parallel": true, "self": 0.00020456299989746185 }, "communicator.exchange": { "total": 0.02575006699998994, "count": 1, "is_parallel": true, "self": 0.02575006699998994 }, "steps_from_proto": { "total": 0.0009552070000609092, "count": 1, "is_parallel": true, "self": 0.0002766820000488224, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006785250000120868, "count": 2, "is_parallel": true, "self": 0.0006785250000120868 } } } } } } }, "UnityEnvironment.step": { "total": 1162.6486454048963, "count": 231321, "is_parallel": true, "self": 34.39001131182772, "children": { "UnityEnvironment._generate_step_input": { "total": 74.42579087292665, "count": 231321, "is_parallel": true, "self": 74.42579087292665 }, "communicator.exchange": { "total": 962.3054416501334, "count": 231321, "is_parallel": true, "self": 962.3054416501334 }, "steps_from_proto": { "total": 91.52740157000858, "count": 231321, "is_parallel": true, "self": 37.49607249120504, "children": { "_process_rank_one_or_two_observation": { "total": 54.03132907880354, "count": 462642, "is_parallel": true, "self": 54.03132907880354 } } } } } } } } } } }, "trainer_advance": { "total": 453.80999327496784, "count": 231322, "self": 5.794620224915207, "children": { "process_trajectory": { "total": 139.94325552605324, "count": 231322, "self": 139.4778701360533, "children": { "RLTrainer._checkpoint": { "total": 0.4653853899999376, "count": 4, "self": 0.4653853899999376 } } }, "_update_policy": { "total": 308.0721175239994, "count": 96, "self": 255.29030734399817, "children": { "TorchPPOOptimizer.update": { "total": 52.78181018000123, "count": 2880, "self": 52.78181018000123 } } } } } } }, "trainer_threads": { "total": 9.58000327955233e-07, "count": 1, "self": 9.58000327955233e-07 }, "TrainerController._save_models": { "total": 0.10852067699988766, "count": 1, "self": 0.0019262840000919823, "children": { "RLTrainer._checkpoint": { "total": 0.10659439299979567, "count": 1, "self": 0.10659439299979567 } } } } } } }