{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8452509045600891, "min": 0.8427199721336365, "max": 2.849993944168091, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8033.2646484375, "min": 8033.2646484375, "max": 29092.73828125, "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": 12.022591590881348, "min": 0.3889586329460144, "max": 12.022591590881348, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2344.4052734375, "min": 75.45797729492188, "max": 2426.80224609375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06685077535232767, "min": 0.06137131464227637, "max": 0.07203934680081005, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2674031014093107, "min": 0.2636319061874768, "max": 0.3601967340040502, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1930638197809458, "min": 0.11037608110642644, "max": 0.28323042994620756, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7722552791237832, "min": 0.44150432442570575, "max": 1.4161521497310379, "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": 23.5, "min": 3.3181818181818183, "max": 23.672727272727272, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1034.0, "min": 146.0, "max": 1302.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.5, "min": 3.3181818181818183, "max": 23.672727272727272, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1034.0, "min": 146.0, "max": 1302.0, "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": "1737518402", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/julio/miniconda3/envs/ml_agents/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737518747" }, "total": 316.012207457, "count": 1, "self": 0.16676501799997823, "children": { "run_training.setup": { "total": 0.007631983000010223, "count": 1, "self": 0.007631983000010223 }, "TrainerController.start_learning": { "total": 315.837810456, "count": 1, "self": 0.16344625599901974, "children": { "TrainerController._reset_env": { "total": 0.9563430690000132, "count": 1, "self": 0.9563430690000132 }, "TrainerController.advance": { "total": 314.679290203001, "count": 18192, "self": 0.1485900680028749, "children": { "env_step": { "total": 249.60292465199984, "count": 18192, "self": 188.9915576939964, "children": { "SubprocessEnvManager._take_step": { "total": 60.50506994000358, "count": 18192, "self": 0.5146301310067543, "children": { "TorchPolicy.evaluate": { "total": 59.990439808996825, "count": 18192, "self": 59.990439808996825 } } }, "workers": { "total": 0.10629701799985014, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 315.13031652599807, "count": 18192, "is_parallel": true, "self": 136.36318442399255, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011369099999569698, "count": 1, "is_parallel": true, "self": 0.00036921099990649964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007676990000504702, "count": 10, "is_parallel": true, "self": 0.0007676990000504702 } } }, "UnityEnvironment.step": { "total": 0.017010643999981312, "count": 1, "is_parallel": true, "self": 0.00013316000001850625, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001250959999765655, "count": 1, "is_parallel": true, "self": 0.0001250959999765655 }, "communicator.exchange": { "total": 0.016299188999994385, "count": 1, "is_parallel": true, "self": 0.016299188999994385 }, "steps_from_proto": { "total": 0.0004531989999918551, "count": 1, "is_parallel": true, "self": 0.00010222699989981265, "children": { "_process_rank_one_or_two_observation": { "total": 0.00035097200009204244, "count": 10, "is_parallel": true, "self": 0.00035097200009204244 } } } } } } }, "UnityEnvironment.step": { "total": 178.76713210200552, "count": 18191, "is_parallel": true, "self": 2.086100771005647, "children": { "UnityEnvironment._generate_step_input": { "total": 1.2389300029976766, "count": 18191, "is_parallel": true, "self": 1.2389300029976766 }, "communicator.exchange": { "total": 169.36859646800292, "count": 18191, "is_parallel": true, "self": 169.36859646800292 }, "steps_from_proto": { "total": 6.073504859999275, "count": 18191, "is_parallel": true, "self": 1.3505732760208389, "children": { "_process_rank_one_or_two_observation": { "total": 4.722931583978436, "count": 181910, "is_parallel": true, "self": 4.722931583978436 } } } } } } } } } } }, "trainer_advance": { "total": 64.9277754829983, "count": 18192, "self": 0.209270711997533, "children": { "process_trajectory": { "total": 14.450874127001157, "count": 18192, "self": 14.269707171001244, "children": { "RLTrainer._checkpoint": { "total": 0.18116695599991317, "count": 4, "self": 0.18116695599991317 } } }, "_update_policy": { "total": 50.26763064399961, "count": 90, "self": 11.959333706998734, "children": { "TorchPPOOptimizer.update": { "total": 38.308296937000875, "count": 4587, "self": 38.308296937000875 } } } } } } }, "trainer_threads": { "total": 4.959999841958052e-07, "count": 1, "self": 4.959999841958052e-07 }, "TrainerController._save_models": { "total": 0.03873043199996573, "count": 1, "self": 0.0004460069999367988, "children": { "RLTrainer._checkpoint": { "total": 0.03828442500002893, "count": 1, "self": 0.03828442500002893 } } } } } } }