{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4113880395889282, "min": 1.4113880395889282, "max": 1.4322775602340698, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71543.2578125, "min": 69306.9140625, "max": 76878.109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.92215568862275, "min": 86.17247386759581, "max": 397.3174603174603, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50061.0, "min": 48933.0, "max": 50065.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999933.0, "min": 49956.0, "max": 1999933.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999933.0, "min": 49956.0, "max": 1999933.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4416239261627197, "min": -0.0004657523531932384, "max": 2.461949586868286, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1223.2535400390625, "min": -0.05821904540061951, "max": 1392.7803955078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.83289276375742, "min": 1.874917497396469, "max": 3.929951753405576, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1920.2792746424675, "min": 234.36468717455864, "max": 2209.8422433137894, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.83289276375742, "min": 1.874917497396469, "max": 3.929951753405576, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1920.2792746424675, "min": 234.36468717455864, "max": 2209.8422433137894, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015953070044310555, "min": 0.014301792579418464, "max": 0.019485313445329666, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047859210132931665, "min": 0.028614080121769803, "max": 0.05633491345700653, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050717985091937916, "min": 0.021569807982693118, "max": 0.05653428578128418, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15215395527581374, "min": 0.043139615965386235, "max": 0.15960436897973218, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.524198825300008e-06, "min": 3.524198825300008e-06, "max": 0.0002952075015975, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0572596475900024e-05, "min": 1.0572596475900024e-05, "max": 0.0008437015687661498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011747, "min": 0.1011747, "max": 0.19840250000000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035241, "min": 0.2074851, "max": 0.58123385, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.861753000000013e-05, "min": 6.861753000000013e-05, "max": 0.00492028475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002058525900000004, "min": 0.0002058525900000004, "max": 0.014063569114999997, "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": "1670895484", "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": "1670897769" }, "total": 2284.9811351480002, "count": 1, "self": 0.39303496100046686, "children": { "run_training.setup": { "total": 0.11167319300000145, "count": 1, "self": 0.11167319300000145 }, "TrainerController.start_learning": { "total": 2284.4764269939997, "count": 1, "self": 4.111210772009599, "children": { "TrainerController._reset_env": { "total": 11.183585375000007, "count": 1, "self": 11.183585375000007 }, "TrainerController.advance": { "total": 2269.06724824899, "count": 232203, "self": 4.161421165049887, "children": { "env_step": { "total": 1788.2823563930056, "count": 232203, "self": 1505.2078554231075, "children": { "SubprocessEnvManager._take_step": { "total": 280.3369982310004, "count": 232203, "self": 14.959444338024241, "children": { "TorchPolicy.evaluate": { "total": 265.37755389297615, "count": 223092, "self": 66.7931916820043, "children": { "TorchPolicy.sample_actions": { "total": 198.58436221097185, "count": 223092, "self": 198.58436221097185 } } } } }, "workers": { "total": 2.737502738897774, "count": 232203, "self": 0.0, "children": { "worker_root": { "total": 2276.467609930975, "count": 232203, "is_parallel": true, "self": 1037.716787167955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002750014000014289, "count": 1, "is_parallel": true, "self": 0.00045821999998452156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022917940000297676, "count": 2, "is_parallel": true, "self": 0.0022917940000297676 } } }, "UnityEnvironment.step": { "total": 0.02754066300002478, "count": 1, "is_parallel": true, "self": 0.0002884770000832759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002003199999762728, "count": 1, "is_parallel": true, "self": 0.0002003199999762728 }, "communicator.exchange": { "total": 0.02635386299999709, "count": 1, "is_parallel": true, "self": 0.02635386299999709 }, "steps_from_proto": { "total": 0.0006980029999681392, "count": 1, "is_parallel": true, "self": 0.000242024999977275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004559779999908642, "count": 2, "is_parallel": true, "self": 0.0004559779999908642 } } } } } } }, "UnityEnvironment.step": { "total": 1238.7508227630199, "count": 232202, "is_parallel": true, "self": 35.41032925082527, "children": { "UnityEnvironment._generate_step_input": { "total": 75.39216742308253, "count": 232202, "is_parallel": true, "self": 75.39216742308253 }, "communicator.exchange": { "total": 1033.7810048120919, "count": 232202, "is_parallel": true, "self": 1033.7810048120919 }, "steps_from_proto": { "total": 94.16732127702011, "count": 232202, "is_parallel": true, "self": 38.371744353901704, "children": { "_process_rank_one_or_two_observation": { "total": 55.795576923118404, "count": 464404, "is_parallel": true, "self": 55.795576923118404 } } } } } } } } } } }, "trainer_advance": { "total": 476.6234706909346, "count": 232203, "self": 6.642933776861582, "children": { "process_trajectory": { "total": 149.36533319607338, "count": 232203, "self": 148.8810959200738, "children": { "RLTrainer._checkpoint": { "total": 0.48423727599958966, "count": 4, "self": 0.48423727599958966 } } }, "_update_policy": { "total": 320.61520371799963, "count": 97, "self": 265.9588920350146, "children": { "TorchPPOOptimizer.update": { "total": 54.656311682985006, "count": 2910, "self": 54.656311682985006 } } } } } } }, "trainer_threads": { "total": 7.810003808117472e-07, "count": 1, "self": 7.810003808117472e-07 }, "TrainerController._save_models": { "total": 0.11438181699986671, "count": 1, "self": 0.0027333660000294913, "children": { "RLTrainer._checkpoint": { "total": 0.11164845099983722, "count": 1, "self": 0.11164845099983722 } } } } } } }