{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4092423915863037, "min": 1.4092423915863037, "max": 1.4291882514953613, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71390.8125, "min": 68437.6484375, "max": 75974.0, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.90655737704918, "min": 76.61705426356589, "max": 403.241935483871, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49353.0, "min": 48738.0, "max": 50126.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999966.0, "min": 49445.0, "max": 1999966.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999966.0, "min": 49445.0, "max": 1999966.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4690284729003906, "min": 0.16557501256465912, "max": 2.4964346885681152, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1506.1072998046875, "min": 20.365726470947266, "max": 1554.9517822265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8675380763460376, "min": 1.8820733815673891, "max": 4.032343415338166, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2359.198226571083, "min": 231.49502593278885, "max": 2448.0385224223137, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8675380763460376, "min": 1.8820733815673891, "max": 4.032343415338166, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2359.198226571083, "min": 231.49502593278885, "max": 2448.0385224223137, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01682784498391104, "min": 0.012507451920798, "max": 0.0198281340100948, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05048353495173312, "min": 0.025014903841596, "max": 0.0594844020302844, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057413071932064165, "min": 0.020731746902068457, "max": 0.06199606787413359, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1722392157961925, "min": 0.041463493804136914, "max": 0.17694208274284998, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.777898740733332e-06, "min": 3.777898740733332e-06, "max": 0.00029538495153835006, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1333696222199995e-05, "min": 1.1333696222199995e-05, "max": 0.0008441469186177, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125926666666668, "min": 0.10125926666666668, "max": 0.19846165, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30377780000000004, "min": 0.20765799999999998, "max": 0.5813823, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.283740666666663e-05, "min": 7.283740666666663e-05, "max": 0.004923236335, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021851221999999988, "min": 0.00021851221999999988, "max": 0.014070976769999998, "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": "1671420442", "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 /content/ml-agents/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": "1671422723" }, "total": 2280.69694149, "count": 1, "self": 0.388885326000036, "children": { "run_training.setup": { "total": 0.1027943399999458, "count": 1, "self": 0.1027943399999458 }, "TrainerController.start_learning": { "total": 2280.205261824, "count": 1, "self": 4.055310449974968, "children": { "TrainerController._reset_env": { "total": 8.082320880999987, "count": 1, "self": 8.082320880999987 }, "TrainerController.advance": { "total": 2267.9532346780247, "count": 232848, "self": 4.3283872249771775, "children": { "env_step": { "total": 1792.6314941129958, "count": 232848, "self": 1507.6750820921195, "children": { "SubprocessEnvManager._take_step": { "total": 282.2069708199872, "count": 232848, "self": 14.622279345958418, "children": { "TorchPolicy.evaluate": { "total": 267.5846914740288, "count": 222960, "self": 66.43113847700295, "children": { "TorchPolicy.sample_actions": { "total": 201.15355299702583, "count": 222960, "self": 201.15355299702583 } } } } }, "workers": { "total": 2.749441200889123, "count": 232848, "self": 0.0, "children": { "worker_root": { "total": 2271.9929291239177, "count": 232848, "is_parallel": true, "self": 1033.0415846918934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003461925000010524, "count": 1, "is_parallel": true, "self": 0.00034985300010248466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031120719999080393, "count": 2, "is_parallel": true, "self": 0.0031120719999080393 } } }, "UnityEnvironment.step": { "total": 0.07057537299999694, "count": 1, "is_parallel": true, "self": 0.00030869999989135977, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017383500005507813, "count": 1, "is_parallel": true, "self": 0.00017383500005507813 }, "communicator.exchange": { "total": 0.0691910729999563, "count": 1, "is_parallel": true, "self": 0.0691910729999563 }, "steps_from_proto": { "total": 0.0009017650000942012, "count": 1, "is_parallel": true, "self": 0.00028566600019530597, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006160989998988953, "count": 2, "is_parallel": true, "self": 0.0006160989998988953 } } } } } } }, "UnityEnvironment.step": { "total": 1238.9513444320244, "count": 232847, "is_parallel": true, "self": 35.34491313900685, "children": { "UnityEnvironment._generate_step_input": { "total": 81.27526524399389, "count": 232847, "is_parallel": true, "self": 81.27526524399389 }, "communicator.exchange": { "total": 1025.943211351987, "count": 232847, "is_parallel": true, "self": 1025.943211351987 }, "steps_from_proto": { "total": 96.38795469703643, "count": 232847, "is_parallel": true, "self": 42.00292248703704, "children": { "_process_rank_one_or_two_observation": { "total": 54.385032209999395, "count": 465694, "is_parallel": true, "self": 54.385032209999395 } } } } } } } } } } }, "trainer_advance": { "total": 470.9933533400516, "count": 232848, "self": 6.426083719150029, "children": { "process_trajectory": { "total": 156.57822669290135, "count": 232848, "self": 155.40452949290216, "children": { "RLTrainer._checkpoint": { "total": 1.1736971999991965, "count": 10, "self": 1.1736971999991965 } } }, "_update_policy": { "total": 307.98904292800023, "count": 97, "self": 254.96786106399622, "children": { "TorchPPOOptimizer.update": { "total": 53.02118186400401, "count": 2910, "self": 53.02118186400401 } } } } } } }, "trainer_threads": { "total": 8.500001058564521e-07, "count": 1, "self": 8.500001058564521e-07 }, "TrainerController._save_models": { "total": 0.11439496499997404, "count": 1, "self": 0.001968167000086396, "children": { "RLTrainer._checkpoint": { "total": 0.11242679799988764, "count": 1, "self": 0.11242679799988764 } } } } } } }