{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4031484127044678, "min": 1.4031484127044678, "max": 1.4281752109527588, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70592.3984375, "min": 68801.796875, "max": 77171.7109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.85416666666667, "min": 76.27975270479135, "max": 434.24347826086955, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49452.0, "min": 49283.0, "max": 49938.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999960.0, "min": 49440.0, "max": 1999960.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999960.0, "min": 49440.0, "max": 1999960.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.396602153778076, "min": 0.19020430743694305, "max": 2.504032611846924, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1380.44287109375, "min": 21.683290481567383, "max": 1570.2100830078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.721121885917253, "min": 1.8809119023774798, "max": 4.040193916619764, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2143.3662062883377, "min": 214.42395687103271, "max": 2498.0370424985886, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.721121885917253, "min": 1.8809119023774798, "max": 4.040193916619764, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2143.3662062883377, "min": 214.42395687103271, "max": 2498.0370424985886, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014558405215252099, "min": 0.012747583949446077, "max": 0.02086735934135504, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0436752156457563, "min": 0.025495167898892154, "max": 0.05628231060594165, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053878378081652856, "min": 0.021616600826382636, "max": 0.062359674274921416, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16163513424495857, "min": 0.04323320165276527, "max": 0.1794832987089952, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6411487863166666e-06, "min": 3.6411487863166666e-06, "max": 0.0002953200015599999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.092344635895e-05, "min": 1.092344635895e-05, "max": 0.00084408916863695, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121368333333335, "min": 0.10121368333333335, "max": 0.19844000000000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30364105, "min": 0.20758335000000006, "max": 0.5813630500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.056279833333337e-05, "min": 7.056279833333337e-05, "max": 0.004922155999999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002116883950000001, "min": 0.0002116883950000001, "max": 0.014070016195000002, "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": "1701759149", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701761592" }, "total": 2442.219101664, "count": 1, "self": 0.39217000999997254, "children": { "run_training.setup": { "total": 0.059951102000013634, "count": 1, "self": 0.059951102000013634 }, "TrainerController.start_learning": { "total": 2441.766980552, "count": 1, "self": 4.4181815199376615, "children": { "TrainerController._reset_env": { "total": 4.246004287000005, "count": 1, "self": 4.246004287000005 }, "TrainerController.advance": { "total": 2433.003980122063, "count": 232795, "self": 4.761376579958323, "children": { "env_step": { "total": 1922.8458984580668, "count": 232795, "self": 1592.7583551832104, "children": { "SubprocessEnvManager._take_step": { "total": 327.27885895300574, "count": 232795, "self": 17.095508699071388, "children": { "TorchPolicy.evaluate": { "total": 310.18335025393435, "count": 222975, "self": 310.18335025393435 } } }, "workers": { "total": 2.8086843218507056, "count": 232795, "self": 0.0, "children": { "worker_root": { "total": 2434.1330678809045, "count": 232795, "is_parallel": true, "self": 1143.8987401988231, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009145059998445504, "count": 1, "is_parallel": true, "self": 0.0002661839996562776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006483220001882728, "count": 2, "is_parallel": true, "self": 0.0006483220001882728 } } }, "UnityEnvironment.step": { "total": 0.031639650999977675, "count": 1, "is_parallel": true, "self": 0.0003176719997100008, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021902700018472387, "count": 1, "is_parallel": true, "self": 0.00021902700018472387 }, "communicator.exchange": { "total": 0.030416277000085756, "count": 1, "is_parallel": true, "self": 0.030416277000085756 }, "steps_from_proto": { "total": 0.0006866749999971944, "count": 1, "is_parallel": true, "self": 0.00019703599991771625, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004896390000794781, "count": 2, "is_parallel": true, "self": 0.0004896390000794781 } } } } } } }, "UnityEnvironment.step": { "total": 1290.2343276820814, "count": 232794, "is_parallel": true, "self": 40.69343604015012, "children": { "UnityEnvironment._generate_step_input": { "total": 83.359209814927, "count": 232794, "is_parallel": true, "self": 83.359209814927 }, "communicator.exchange": { "total": 1075.3825242990383, "count": 232794, "is_parallel": true, "self": 1075.3825242990383 }, "steps_from_proto": { "total": 90.79915752796592, "count": 232794, "is_parallel": true, "self": 32.187551758190466, "children": { "_process_rank_one_or_two_observation": { "total": 58.61160576977545, "count": 465588, "is_parallel": true, "self": 58.61160576977545 } } } } } } } } } } }, "trainer_advance": { "total": 505.39670508403765, "count": 232795, "self": 6.824676491933587, "children": { "process_trajectory": { "total": 158.15496228810548, "count": 232795, "self": 156.98490748410518, "children": { "RLTrainer._checkpoint": { "total": 1.1700548040003014, "count": 10, "self": 1.1700548040003014 } } }, "_update_policy": { "total": 340.4170663039986, "count": 97, "self": 277.2789462460132, "children": { "TorchPPOOptimizer.update": { "total": 63.13812005798536, "count": 2910, "self": 63.13812005798536 } } } } } } }, "trainer_threads": { "total": 8.339998203155119e-07, "count": 1, "self": 8.339998203155119e-07 }, "TrainerController._save_models": { "total": 0.09881378899990523, "count": 1, "self": 0.0016900179998629028, "children": { "RLTrainer._checkpoint": { "total": 0.09712377100004232, "count": 1, "self": 0.09712377100004232 } } } } } } }