{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1937764883041382, "min": 1.1937764883041382, "max": 2.8456976413726807, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12277.9912109375, "min": 11713.3271484375, "max": 29142.7890625, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.975739479064941, "min": 0.33558693528175354, "max": 9.975739479064941, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2045.026611328125, "min": 65.10386657714844, "max": 2045.026611328125, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06423522809775166, "min": 0.06325333213031877, "max": 0.07449955683000108, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3211761404887583, "min": 0.25301332852127506, "max": 0.36037536319482194, "count": 15 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19547617225085986, "min": 0.13929614012458308, "max": 0.26997192075439524, "count": 15 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9773808612542993, "min": 0.5571845604983323, "max": 1.3498596037719763, "count": 15 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.776096741333334e-06, "min": 9.776096741333334e-06, "max": 0.000289176003608, "count": 15 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.888048370666667e-05, "min": 4.888048370666667e-05, "max": 0.0013468800510399999, "count": 15 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10325866666666668, "min": 0.10325866666666668, "max": 0.19639199999999998, "count": 15 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5162933333333334, "min": 0.43943466666666664, "max": 0.94896, "count": 15 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00017260746666666673, "min": 0.00017260746666666673, "max": 0.004819960799999999, "count": 15 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008630373333333337, "min": 0.0008630373333333337, "max": 0.022453104, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.654545454545456, "min": 3.5454545454545454, "max": 20.477272727272727, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1081.0, "min": 156.0, "max": 1081.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.654545454545456, "min": 3.5454545454545454, "max": 20.477272727272727, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1081.0, "min": 156.0, "max": 1081.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704164813", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704165169" }, "total": 355.320592576, "count": 1, "self": 0.8030569020000939, "children": { "run_training.setup": { "total": 0.056347005999953126, "count": 1, "self": 0.056347005999953126 }, "TrainerController.start_learning": { "total": 354.461188668, "count": 1, "self": 0.4946137269914175, "children": { "TrainerController._reset_env": { "total": 3.5410507089999896, "count": 1, "self": 3.5410507089999896 }, "TrainerController.advance": { "total": 350.28971699500846, "count": 13679, "self": 0.23310059000596084, "children": { "env_step": { "total": 350.0566164050025, "count": 13679, "self": 230.2338112200003, "children": { "SubprocessEnvManager._take_step": { "total": 119.59204880399773, "count": 13679, "self": 1.1749995989891318, "children": { "TorchPolicy.evaluate": { "total": 118.4170492050086, "count": 13679, "self": 118.4170492050086 } } }, "workers": { "total": 0.2307563810044826, "count": 13679, "self": 0.0, "children": { "worker_root": { "total": 353.3937458229955, "count": 13679, "is_parallel": true, "self": 173.75305906199276, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005550454999990961, "count": 1, "is_parallel": true, "self": 0.004005683999935172, "children": { "_process_rank_one_or_two_observation": { "total": 0.001544771000055789, "count": 10, "is_parallel": true, "self": 0.001544771000055789 } } }, "UnityEnvironment.step": { "total": 0.06687598399997796, "count": 1, "is_parallel": true, "self": 0.0007175909999546093, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003548710000131905, "count": 1, "is_parallel": true, "self": 0.0003548710000131905 }, "communicator.exchange": { "total": 0.06392826500001547, "count": 1, "is_parallel": true, "self": 0.06392826500001547 }, "steps_from_proto": { "total": 0.00187525699999469, "count": 1, "is_parallel": true, "self": 0.00033505000004652175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015402069999481682, "count": 10, "is_parallel": true, "self": 0.0015402069999481682 } } } } } } }, "UnityEnvironment.step": { "total": 179.64068676100277, "count": 13678, "is_parallel": true, "self": 8.50917406001355, "children": { "UnityEnvironment._generate_step_input": { "total": 4.204993396999043, "count": 13678, "is_parallel": true, "self": 4.204993396999043 }, "communicator.exchange": { "total": 140.19035022099536, "count": 13678, "is_parallel": true, "self": 140.19035022099536 }, "steps_from_proto": { "total": 26.73616908299482, "count": 13678, "is_parallel": true, "self": 5.102301030977571, "children": { "_process_rank_one_or_two_observation": { "total": 21.63386805201725, "count": 136780, "is_parallel": true, "self": 21.63386805201725 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022416900003463525, "count": 1, "self": 0.00022416900003463525, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 345.89370532599105, "count": 537644, "is_parallel": true, "self": 11.209023859960723, "children": { "process_trajectory": { "total": 190.4684337520303, "count": 537644, "is_parallel": true, "self": 189.8690282320303, "children": { "RLTrainer._checkpoint": { "total": 0.5994055200000048, "count": 3, "is_parallel": true, "self": 0.5994055200000048 } } }, "_update_policy": { "total": 144.21624771400002, "count": 68, "is_parallel": true, "self": 45.041235942997105, "children": { "TorchPPOOptimizer.update": { "total": 99.17501177100291, "count": 3465, "is_parallel": true, "self": 99.17501177100291 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13558306800007358, "count": 1, "self": 0.0015248200000996803, "children": { "RLTrainer._checkpoint": { "total": 0.1340582479999739, "count": 1, "self": 0.1340582479999739 } } } } } } }