{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9118658304214478, "min": 0.89549320936203, "max": 2.8518598079681396, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8666.373046875, "min": 8666.373046875, "max": 29111.78515625, "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": 13.177143096923828, "min": 0.36337044835090637, "max": 13.177143096923828, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2569.54296875, "min": 70.49386596679688, "max": 2687.5322265625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05987863670452498, "min": 0.05987863670452498, "max": 0.07550312518364723, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.23951454681809992, "min": 0.23951454681809992, "max": 0.3775156259182361, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23068397083118852, "min": 0.10636232049243213, "max": 0.28024065728281056, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9227358833247541, "min": 0.42544928196972853, "max": 1.2245127190561855, "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": 25.5, "min": 3.0, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 132.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 3.0, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 132.0, "max": 1417.0, "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": "1750334765", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750335237" }, "total": 472.42420688, "count": 1, "self": 0.42733578199994326, "children": { "run_training.setup": { "total": 0.02165976900005262, "count": 1, "self": 0.02165976900005262 }, "TrainerController.start_learning": { "total": 471.975211329, "count": 1, "self": 0.4117504800049687, "children": { "TrainerController._reset_env": { "total": 2.081813526000019, "count": 1, "self": 2.081813526000019 }, "TrainerController.advance": { "total": 469.39152770999505, "count": 18192, "self": 0.44034819098561684, "children": { "env_step": { "total": 337.41831338900215, "count": 18192, "self": 259.2917776039822, "children": { "SubprocessEnvManager._take_step": { "total": 77.88391608200408, "count": 18192, "self": 1.3852040070090084, "children": { "TorchPolicy.evaluate": { "total": 76.49871207499507, "count": 18192, "self": 76.49871207499507 } } }, "workers": { "total": 0.2426197030158619, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 469.986186083999, "count": 18192, "is_parallel": true, "self": 242.51586252698797, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021987559999843143, "count": 1, "is_parallel": true, "self": 0.000682367000024442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015163889999598723, "count": 10, "is_parallel": true, "self": 0.0015163889999598723 } } }, "UnityEnvironment.step": { "total": 0.07267303399999037, "count": 1, "is_parallel": true, "self": 0.0006348299999672236, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004327049999801602, "count": 1, "is_parallel": true, "self": 0.0004327049999801602 }, "communicator.exchange": { "total": 0.06940554900000961, "count": 1, "is_parallel": true, "self": 0.06940554900000961 }, "steps_from_proto": { "total": 0.0021999500000333683, "count": 1, "is_parallel": true, "self": 0.0004360420000466547, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017639079999867135, "count": 10, "is_parallel": true, "self": 0.0017639079999867135 } } } } } } }, "UnityEnvironment.step": { "total": 227.470323557011, "count": 18191, "is_parallel": true, "self": 10.631709639025019, "children": { "UnityEnvironment._generate_step_input": { "total": 6.025030793995256, "count": 18191, "is_parallel": true, "self": 6.025030793995256 }, "communicator.exchange": { "total": 175.0300370349961, "count": 18191, "is_parallel": true, "self": 175.0300370349961 }, "steps_from_proto": { "total": 35.783546088994626, "count": 18191, "is_parallel": true, "self": 6.430568098970639, "children": { "_process_rank_one_or_two_observation": { "total": 29.352977990023987, "count": 181910, "is_parallel": true, "self": 29.352977990023987 } } } } } } } } } } }, "trainer_advance": { "total": 131.53286613000728, "count": 18192, "self": 0.47714595900703216, "children": { "process_trajectory": { "total": 30.304337811000437, "count": 18192, "self": 29.76381739600049, "children": { "RLTrainer._checkpoint": { "total": 0.5405204149999463, "count": 4, "self": 0.5405204149999463 } } }, "_update_policy": { "total": 100.75138235999981, "count": 90, "self": 42.11543741399896, "children": { "TorchPPOOptimizer.update": { "total": 58.63594494600085, "count": 4587, "self": 58.63594494600085 } } } } } } }, "trainer_threads": { "total": 1.1360000371496426e-06, "count": 1, "self": 1.1360000371496426e-06 }, "TrainerController._save_models": { "total": 0.09011847699991904, "count": 1, "self": 0.0008169929999439773, "children": { "RLTrainer._checkpoint": { "total": 0.08930148399997506, "count": 1, "self": 0.08930148399997506 } } } } } } }