{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8507553935050964, "min": 0.8501920104026794, "max": 2.843169927597046, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8085.5791015625, "min": 8085.5791015625, "max": 29023.078125, "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": 13.014029502868652, "min": 0.5220280885696411, "max": 13.014029502868652, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.73583984375, "min": 101.27345275878906, "max": 2626.0537109375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06929245526165081, "min": 0.06182131229536882, "max": 0.07257599040167406, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27716982104660326, "min": 0.27188555589607716, "max": 0.3553218233813395, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2037011715126973, "min": 0.1532573709629622, "max": 0.2828538552803152, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8148046860507892, "min": 0.6130294838518489, "max": 1.414269276401576, "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": 25.863636363636363, "min": 4.363636363636363, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1138.0, "min": 192.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.863636363636363, "min": 4.363636363636363, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1138.0, "min": 192.0, "max": 1399.0, "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": "1784127732", "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 --force", "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": "1784128230" }, "total": 497.927473945, "count": 1, "self": 0.4774041200000738, "children": { "run_training.setup": { "total": 0.02542643499998576, "count": 1, "self": 0.02542643499998576 }, "TrainerController.start_learning": { "total": 497.4246433899999, "count": 1, "self": 0.3907097329916951, "children": { "TrainerController._reset_env": { "total": 2.9400365789999796, "count": 1, "self": 2.9400365789999796 }, "TrainerController.advance": { "total": 494.00921511400816, "count": 18192, "self": 0.41373394500760696, "children": { "env_step": { "total": 366.5261208859944, "count": 18192, "self": 288.4116925190026, "children": { "SubprocessEnvManager._take_step": { "total": 77.8738399669993, "count": 18192, "self": 1.3742889810085899, "children": { "TorchPolicy.evaluate": { "total": 76.49955098599071, "count": 18192, "self": 76.49955098599071 } } }, "workers": { "total": 0.2405883999924754, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 495.1890796259935, "count": 18192, "is_parallel": true, "self": 241.4923158329908, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051432410000415985, "count": 1, "is_parallel": true, "self": 0.003426502000252185, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017167389997894134, "count": 10, "is_parallel": true, "self": 0.0017167389997894134 } } }, "UnityEnvironment.step": { "total": 0.041896797000049446, "count": 1, "is_parallel": true, "self": 0.0007123480000927884, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004565839999486343, "count": 1, "is_parallel": true, "self": 0.0004565839999486343 }, "communicator.exchange": { "total": 0.038465982000047916, "count": 1, "is_parallel": true, "self": 0.038465982000047916 }, "steps_from_proto": { "total": 0.0022618829999601076, "count": 1, "is_parallel": true, "self": 0.0004462940000848903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018155889998752173, "count": 10, "is_parallel": true, "self": 0.0018155889998752173 } } } } } } }, "UnityEnvironment.step": { "total": 253.69676379300267, "count": 18191, "is_parallel": true, "self": 11.34231212197983, "children": { "UnityEnvironment._generate_step_input": { "total": 6.085753087003241, "count": 18191, "is_parallel": true, "self": 6.085753087003241 }, "communicator.exchange": { "total": 193.82167664300334, "count": 18191, "is_parallel": true, "self": 193.82167664300334 }, "steps_from_proto": { "total": 42.44702194101626, "count": 18191, "is_parallel": true, "self": 7.190548103019523, "children": { "_process_rank_one_or_two_observation": { "total": 35.25647383799674, "count": 181910, "is_parallel": true, "self": 35.25647383799674 } } } } } } } } } } }, "trainer_advance": { "total": 127.06936028300618, "count": 18192, "self": 0.4867646749951291, "children": { "process_trajectory": { "total": 26.69478271701132, "count": 18192, "self": 26.237997878011242, "children": { "RLTrainer._checkpoint": { "total": 0.45678483900007905, "count": 4, "self": 0.45678483900007905 } } }, "_update_policy": { "total": 99.88781289099973, "count": 90, "self": 40.58280023299301, "children": { "TorchPPOOptimizer.update": { "total": 59.30501265800672, "count": 4587, "self": 59.30501265800672 } } } } } } }, "trainer_threads": { "total": 1.1730001006071689e-06, "count": 1, "self": 1.1730001006071689e-06 }, "TrainerController._save_models": { "total": 0.08468079099998249, "count": 1, "self": 0.0009090389999073523, "children": { "RLTrainer._checkpoint": { "total": 0.08377175200007514, "count": 1, "self": 0.08377175200007514 } } } } } } }