{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0315399169921875, "min": 1.0315399169921875, "max": 2.8590214252471924, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9803.755859375, "min": 9803.755859375, "max": 29184.890625, "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": 12.633161544799805, "min": 0.4193631708621979, "max": 12.633161544799805, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2463.466552734375, "min": 81.35645294189453, "max": 2552.207275390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06815902957361472, "min": 0.0646317145423667, "max": 0.0739977596993056, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2726361182944589, "min": 0.2726361182944589, "max": 0.369988798496528, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2335270165520556, "min": 0.12508904446354685, "max": 0.29416327312880874, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9341080662082224, "min": 0.5003561778541874, "max": 1.4708163656440436, "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": 24.931818181818183, "min": 3.7045454545454546, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 163.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 3.7045454545454546, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 163.0, "max": 1369.0, "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": "1785243470", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785243920" }, "total": 449.97138358300003, "count": 1, "self": 0.43350465800017446, "children": { "run_training.setup": { "total": 0.026655081999933827, "count": 1, "self": 0.026655081999933827 }, "TrainerController.start_learning": { "total": 449.5112238429999, "count": 1, "self": 0.3485010349991171, "children": { "TrainerController._reset_env": { "total": 2.8082207019999714, "count": 1, "self": 2.8082207019999714 }, "TrainerController.advance": { "total": 446.2715246230007, "count": 18192, "self": 0.3588232710080774, "children": { "env_step": { "total": 327.3782583900029, "count": 18192, "self": 257.13740792601516, "children": { "SubprocessEnvManager._take_step": { "total": 70.02599538899335, "count": 18192, "self": 1.2743705969865005, "children": { "TorchPolicy.evaluate": { "total": 68.75162479200685, "count": 18192, "self": 68.75162479200685 } } }, "workers": { "total": 0.21485507499437517, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 447.6395894450036, "count": 18192, "is_parallel": true, "self": 221.75191459498956, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004407361999938075, "count": 1, "is_parallel": true, "self": 0.003050871000141342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013564909997967334, "count": 10, "is_parallel": true, "self": 0.0013564909997967334 } } }, "UnityEnvironment.step": { "total": 0.04578393299993877, "count": 1, "is_parallel": true, "self": 0.0006451690001085808, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041368699999111413, "count": 1, "is_parallel": true, "self": 0.00041368699999111413 }, "communicator.exchange": { "total": 0.04273226199984492, "count": 1, "is_parallel": true, "self": 0.04273226199984492 }, "steps_from_proto": { "total": 0.0019928149999941525, "count": 1, "is_parallel": true, "self": 0.0003826749998552259, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016101400001389266, "count": 10, "is_parallel": true, "self": 0.0016101400001389266 } } } } } } }, "UnityEnvironment.step": { "total": 225.88767485001404, "count": 18191, "is_parallel": true, "self": 10.290116467992448, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5354561919934895, "count": 18191, "is_parallel": true, "self": 5.5354561919934895 }, "communicator.exchange": { "total": 172.81168541801708, "count": 18191, "is_parallel": true, "self": 172.81168541801708 }, "steps_from_proto": { "total": 37.25041677201102, "count": 18191, "is_parallel": true, "self": 6.682631421982023, "children": { "_process_rank_one_or_two_observation": { "total": 30.567785350029, "count": 181910, "is_parallel": true, "self": 30.567785350029 } } } } } } } } } } }, "trainer_advance": { "total": 118.53444296198973, "count": 18192, "self": 0.4327078449646251, "children": { "process_trajectory": { "total": 23.991195449024872, "count": 18192, "self": 23.56111488002489, "children": { "RLTrainer._checkpoint": { "total": 0.43008056899998337, "count": 4, "self": 0.43008056899998337 } } }, "_update_policy": { "total": 94.11053966800023, "count": 90, "self": 38.57147961299506, "children": { "TorchPPOOptimizer.update": { "total": 55.539060055005166, "count": 4587, "self": 55.539060055005166 } } } } } } }, "trainer_threads": { "total": 1.100999952541315e-06, "count": 1, "self": 1.100999952541315e-06 }, "TrainerController._save_models": { "total": 0.08297638200019719, "count": 1, "self": 0.000755580000259215, "children": { "RLTrainer._checkpoint": { "total": 0.08222080199993798, "count": 1, "self": 0.08222080199993798 } } } } } } }