{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.397922158241272, "min": 1.397922158241272, "max": 1.4312586784362793, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69142.625, "min": 69107.5, "max": 76946.96875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.71212121212122, "min": 78.64012738853503, "max": 392.609375, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49480.0, "min": 48838.0, "max": 50254.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999900.0, "min": 49745.0, "max": 1999900.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999900.0, "min": 49745.0, "max": 1999900.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4624133110046387, "min": 0.09397322684526443, "max": 2.491986036300659, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1300.1541748046875, "min": 11.934599876403809, "max": 1522.229736328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7418765282314834, "min": 1.792153951689953, "max": 3.9533077907481298, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1975.7108069062233, "min": 227.60355186462402, "max": 2400.35407525301, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7418765282314834, "min": 1.792153951689953, "max": 3.9533077907481298, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1975.7108069062233, "min": 227.60355186462402, "max": 2400.35407525301, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019392815286604068, "min": 0.012781871920014964, "max": 0.023113890756697703, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0581784458598122, "min": 0.025563743840029927, "max": 0.0581784458598122, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04937003176245425, "min": 0.02119393227621913, "max": 0.05290207792487409, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14811009528736274, "min": 0.04238786455243826, "max": 0.15870623377462229, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2960989013333323e-06, "min": 3.2960989013333323e-06, "max": 0.0002952611265796249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.888296703999996e-06, "min": 9.888296703999996e-06, "max": 0.0008438059687313499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109866666666667, "min": 0.10109866666666667, "max": 0.1984203750000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.303296, "min": 0.20732829999999997, "max": 0.58126865, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.482346666666665e-05, "min": 6.482346666666665e-05, "max": 0.004921176712500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019447039999999995, "min": 0.00019447039999999995, "max": 0.014065305635, "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": "1678103891", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "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": "1.22.4", "end_time_seconds": "1678106227" }, "total": 2336.5518939830004, "count": 1, "self": 0.4419552819999808, "children": { "run_training.setup": { "total": 0.11022889499997746, "count": 1, "self": 0.11022889499997746 }, "TrainerController.start_learning": { "total": 2335.9997098060003, "count": 1, "self": 4.0729869680467345, "children": { "TrainerController._reset_env": { "total": 9.693196510000007, "count": 1, "self": 9.693196510000007 }, "TrainerController.advance": { "total": 2322.0059947159534, "count": 232524, "self": 4.545217938987662, "children": { "env_step": { "total": 1798.7743893689326, "count": 232524, "self": 1481.6743412179308, "children": { "SubprocessEnvManager._take_step": { "total": 314.3851871860129, "count": 232524, "self": 15.211921737969874, "children": { "TorchPolicy.evaluate": { "total": 299.173265448043, "count": 222950, "self": 68.52829682901017, "children": { "TorchPolicy.sample_actions": { "total": 230.64496861903285, "count": 222950, "self": 230.64496861903285 } } } } }, "workers": { "total": 2.714860964989043, "count": 232524, "self": 0.0, "children": { "worker_root": { "total": 2327.912389342008, "count": 232524, "is_parallel": true, "self": 1127.2230049958823, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010764240000753489, "count": 1, "is_parallel": true, "self": 0.0004169550002188771, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006594689998564718, "count": 2, "is_parallel": true, "self": 0.0006594689998564718 } } }, "UnityEnvironment.step": { "total": 0.02844275999996171, "count": 1, "is_parallel": true, "self": 0.0003025569999408617, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021042299999862735, "count": 1, "is_parallel": true, "self": 0.00021042299999862735 }, "communicator.exchange": { "total": 0.027220665999948324, "count": 1, "is_parallel": true, "self": 0.027220665999948324 }, "steps_from_proto": { "total": 0.000709114000073896, "count": 1, "is_parallel": true, "self": 0.0002469930001325338, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046212099994136224, "count": 2, "is_parallel": true, "self": 0.00046212099994136224 } } } } } } }, "UnityEnvironment.step": { "total": 1200.6893843461255, "count": 232523, "is_parallel": true, "self": 37.35475229705776, "children": { "UnityEnvironment._generate_step_input": { "total": 76.0880948609115, "count": 232523, "is_parallel": true, "self": 76.0880948609115 }, "communicator.exchange": { "total": 999.5284502860987, "count": 232523, "is_parallel": true, "self": 999.5284502860987 }, "steps_from_proto": { "total": 87.71808690205773, "count": 232523, "is_parallel": true, "self": 35.30600277907615, "children": { "_process_rank_one_or_two_observation": { "total": 52.41208412298158, "count": 465046, "is_parallel": true, "self": 52.41208412298158 } } } } } } } } } } }, "trainer_advance": { "total": 518.6863874080329, "count": 232524, "self": 6.357728744062797, "children": { "process_trajectory": { "total": 163.86669830297092, "count": 232524, "self": 162.04991806097064, "children": { "RLTrainer._checkpoint": { "total": 1.8167802420002772, "count": 10, "self": 1.8167802420002772 } } }, "_update_policy": { "total": 348.4619603609992, "count": 97, "self": 278.39911882799095, "children": { "TorchPPOOptimizer.update": { "total": 70.06284153300828, "count": 2910, "self": 70.06284153300828 } } } } } } }, "trainer_threads": { "total": 8.170000000973232e-07, "count": 1, "self": 8.170000000973232e-07 }, "TrainerController._save_models": { "total": 0.22753079499989326, "count": 1, "self": 0.0037442329999066715, "children": { "RLTrainer._checkpoint": { "total": 0.2237865619999866, "count": 1, "self": 0.2237865619999866 } } } } } } }