{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8145171999931335, "min": 0.8145171999931335, "max": 2.8401098251342773, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7741.17138671875, "min": 7741.17138671875, "max": 28991.841796875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.159931182861328, "min": 0.3976883590221405, "max": 12.159931182861328, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2371.1865234375, "min": 77.15154266357422, "max": 2471.560302734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06948428765398977, "min": 0.06122964530413989, "max": 0.07566719292796786, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2779371506159591, "min": 0.2515506423928766, "max": 0.3623642042070523, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18085917618636993, "min": 0.11479012226895885, "max": 0.32314023499687516, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7234367047454797, "min": 0.4591604890758354, "max": 1.4484485323522605, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.09090909090909, "min": 3.25, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1060.0, "min": 143.0, "max": 1318.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.09090909090909, "min": 3.25, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1060.0, "min": 143.0, "max": 1318.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1743416913", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743417348" }, "total": 434.391875861, "count": 1, "self": 0.4341359669999747, "children": { "run_training.setup": { "total": 0.02420573400002013, "count": 1, "self": 0.02420573400002013 }, "TrainerController.start_learning": { "total": 433.93353416, "count": 1, "self": 0.36863723400540493, "children": { "TrainerController._reset_env": { "total": 3.572441217000005, "count": 1, "self": 3.572441217000005 }, "TrainerController.advance": { "total": 429.89968180499466, "count": 18192, "self": 0.3709011929874464, "children": { "env_step": { "total": 303.0981558339957, "count": 18192, "self": 231.89221612898803, "children": { "SubprocessEnvManager._take_step": { "total": 71.00038235400262, "count": 18192, "self": 1.2603661570031477, "children": { "TorchPolicy.evaluate": { "total": 69.74001619699948, "count": 18192, "self": 69.74001619699948 } } }, "workers": { "total": 0.2055573510050408, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 432.4535004589963, "count": 18192, "is_parallel": true, "self": 228.66716708198783, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006391633000021102, "count": 1, "is_parallel": true, "self": 0.0043684710000206906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020231620000004114, "count": 10, "is_parallel": true, "self": 0.0020231620000004114 } } }, "UnityEnvironment.step": { "total": 0.03513493700000936, "count": 1, "is_parallel": true, "self": 0.0005869839999945725, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038738699998930315, "count": 1, "is_parallel": true, "self": 0.00038738699998930315 }, "communicator.exchange": { "total": 0.03239927900000339, "count": 1, "is_parallel": true, "self": 0.03239927900000339 }, "steps_from_proto": { "total": 0.0017612870000220937, "count": 1, "is_parallel": true, "self": 0.0003445970000370835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014166899999850102, "count": 10, "is_parallel": true, "self": 0.0014166899999850102 } } } } } } }, "UnityEnvironment.step": { "total": 203.78633337700848, "count": 18191, "is_parallel": true, "self": 9.706074180987173, "children": { "UnityEnvironment._generate_step_input": { "total": 5.466242070009002, "count": 18191, "is_parallel": true, "self": 5.466242070009002 }, "communicator.exchange": { "total": 157.56030242800506, "count": 18191, "is_parallel": true, "self": 157.56030242800506 }, "steps_from_proto": { "total": 31.05371469800724, "count": 18191, "is_parallel": true, "self": 5.589608709015465, "children": { "_process_rank_one_or_two_observation": { "total": 25.464105988991776, "count": 181910, "is_parallel": true, "self": 25.464105988991776 } } } } } } } } } } }, "trainer_advance": { "total": 126.43062477801152, "count": 18192, "self": 0.4636448960187636, "children": { "process_trajectory": { "total": 27.071186469993336, "count": 18192, "self": 26.555637640993268, "children": { "RLTrainer._checkpoint": { "total": 0.5155488290000676, "count": 4, "self": 0.5155488290000676 } } }, "_update_policy": { "total": 98.89579341199942, "count": 90, "self": 40.63455404899656, "children": { "TorchPPOOptimizer.update": { "total": 58.26123936300286, "count": 4587, "self": 58.26123936300286 } } } } } } }, "trainer_threads": { "total": 1.0190000239163055e-06, "count": 1, "self": 1.0190000239163055e-06 }, "TrainerController._save_models": { "total": 0.0927728849999312, "count": 1, "self": 0.001211465999858774, "children": { "RLTrainer._checkpoint": { "total": 0.09156141900007242, "count": 1, "self": 0.09156141900007242 } } } } } } }