{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.406950831413269, "min": 1.406950831413269, "max": 1.4296149015426636, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72303.203125, "min": 68678.390625, "max": 77459.859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.49512670565302, "min": 80.70413223140496, "max": 403.93548387096774, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49502.0, "min": 48826.0, "max": 50088.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999901.0, "min": 49853.0, "max": 1999901.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999901.0, "min": 49853.0, "max": 1999901.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.366018295288086, "min": 0.10645351558923721, "max": 2.4451687335968018, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1213.767333984375, "min": 13.093782424926758, "max": 1429.388671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.601452640390303, "min": 1.8501247308118556, "max": 3.894635107677445, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1847.5452045202255, "min": 227.56534188985825, "max": 2273.74380838871, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.601452640390303, "min": 1.8501247308118556, "max": 3.894635107677445, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1847.5452045202255, "min": 227.56534188985825, "max": 2273.74380838871, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016793998557619084, "min": 0.013877953765202419, "max": 0.019835731938373, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050381995672857255, "min": 0.028838045224741413, "max": 0.059507195815119, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049243139641152484, "min": 0.023056502919644117, "max": 0.06987974997609854, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14772941892345745, "min": 0.046113005839288235, "max": 0.18118651472032068, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3571988809666683e-06, "min": 3.3571988809666683e-06, "max": 0.0002953641015453, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0071596642900005e-05, "min": 1.0071596642900005e-05, "max": 0.00084382576872475, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111903333333333, "min": 0.10111903333333333, "max": 0.19845470000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033571, "min": 0.20737525000000004, "max": 0.58127525, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.583976333333337e-05, "min": 6.583976333333337e-05, "max": 0.004922889529999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001975192900000001, "min": 0.0001975192900000001, "max": 0.014065634975000001, "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": "1714289759", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714292377" }, "total": 2617.479521106, "count": 1, "self": 0.4904846049998923, "children": { "run_training.setup": { "total": 0.08148505400001227, "count": 1, "self": 0.08148505400001227 }, "TrainerController.start_learning": { "total": 2616.907551447, "count": 1, "self": 4.716401751941703, "children": { "TrainerController._reset_env": { "total": 3.2323228060000133, "count": 1, "self": 3.2323228060000133 }, "TrainerController.advance": { "total": 2608.8352086820582, "count": 232289, "self": 5.133200721993489, "children": { "env_step": { "total": 2109.443104738053, "count": 232289, "self": 1748.1021904910845, "children": { "SubprocessEnvManager._take_step": { "total": 358.0828807019784, "count": 232289, "self": 18.673871094009883, "children": { "TorchPolicy.evaluate": { "total": 339.4090096079685, "count": 223130, "self": 339.4090096079685 } } }, "workers": { "total": 3.258033544990184, "count": 232289, "self": 0.0, "children": { "worker_root": { "total": 2609.066786217061, "count": 232289, "is_parallel": true, "self": 1200.3786864450576, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017048680000186778, "count": 1, "is_parallel": true, "self": 0.0003977860000077271, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013070820000109507, "count": 2, "is_parallel": true, "self": 0.0013070820000109507 } } }, "UnityEnvironment.step": { "total": 0.034323263000004545, "count": 1, "is_parallel": true, "self": 0.0003890440000304807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021073599998544523, "count": 1, "is_parallel": true, "self": 0.00021073599998544523 }, "communicator.exchange": { "total": 0.03288943199999039, "count": 1, "is_parallel": true, "self": 0.03288943199999039 }, "steps_from_proto": { "total": 0.000834050999998226, "count": 1, "is_parallel": true, "self": 0.00023750800002630967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005965429999719163, "count": 2, "is_parallel": true, "self": 0.0005965429999719163 } } } } } } }, "UnityEnvironment.step": { "total": 1408.6880997720032, "count": 232288, "is_parallel": true, "self": 42.44663581699979, "children": { "UnityEnvironment._generate_step_input": { "total": 93.60878690996492, "count": 232288, "is_parallel": true, "self": 93.60878690996492 }, "communicator.exchange": { "total": 1172.0264126630584, "count": 232288, "is_parallel": true, "self": 1172.0264126630584 }, "steps_from_proto": { "total": 100.60626438197994, "count": 232288, "is_parallel": true, "self": 38.53777290883616, "children": { "_process_rank_one_or_two_observation": { "total": 62.06849147314378, "count": 464576, "is_parallel": true, "self": 62.06849147314378 } } } } } } } } } } }, "trainer_advance": { "total": 494.2589032220118, "count": 232289, "self": 7.189528742972925, "children": { "process_trajectory": { "total": 167.95982756503727, "count": 232289, "self": 166.53539900203683, "children": { "RLTrainer._checkpoint": { "total": 1.424428563000447, "count": 10, "self": 1.424428563000447 } } }, "_update_policy": { "total": 319.10954691400156, "count": 97, "self": 255.2022316450047, "children": { "TorchPPOOptimizer.update": { "total": 63.907315268996854, "count": 2910, "self": 63.907315268996854 } } } } } } }, "trainer_threads": { "total": 1.0170001587539446e-06, "count": 1, "self": 1.0170001587539446e-06 }, "TrainerController._save_models": { "total": 0.12361719000000448, "count": 1, "self": 0.003737662999810709, "children": { "RLTrainer._checkpoint": { "total": 0.11987952700019378, "count": 1, "self": 0.11987952700019378 } } } } } } }