{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7861309051513672, "min": 0.760474443435669, "max": 2.857461929321289, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7471.38818359375, "min": 7471.38818359375, "max": 29168.970703125, "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": 12.894323348999023, "min": 0.4617782235145569, "max": 12.894323348999023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2514.39306640625, "min": 89.58497619628906, "max": 2615.0458984375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06522598571698873, "min": 0.06353011120889135, "max": 0.07587594587433463, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26090394286795493, "min": 0.25853156053320464, "max": 0.36986509379422905, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18953377044960565, "min": 0.14006091173117358, "max": 0.28370574145924815, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7581350817984226, "min": 0.5602436469246943, "max": 1.4185287072962407, "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": 25.431818181818183, "min": 3.840909090909091, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 169.0, "max": 1409.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.840909090909091, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 169.0, "max": 1409.0, "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": "1773200749", "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": "1773201234" }, "total": 485.149690694, "count": 1, "self": 0.4840945639999745, "children": { "run_training.setup": { "total": 0.027774794000038128, "count": 1, "self": 0.027774794000038128 }, "TrainerController.start_learning": { "total": 484.637821336, "count": 1, "self": 0.3679394230013031, "children": { "TrainerController._reset_env": { "total": 3.9667469409999967, "count": 1, "self": 3.9667469409999967 }, "TrainerController.advance": { "total": 480.22092718799865, "count": 18192, "self": 0.39386874699891905, "children": { "env_step": { "total": 346.09042081199607, "count": 18192, "self": 270.08419262899406, "children": { "SubprocessEnvManager._take_step": { "total": 75.78262440400147, "count": 18192, "self": 1.3762860770066254, "children": { "TorchPolicy.evaluate": { "total": 74.40633832699484, "count": 18192, "self": 74.40633832699484 } } }, "workers": { "total": 0.22360377900054118, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 482.62598910901363, "count": 18192, "is_parallel": true, "self": 244.60429695901576, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005660695000074156, "count": 1, "is_parallel": true, "self": 0.003390299999978197, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022703950000959594, "count": 10, "is_parallel": true, "self": 0.0022703950000959594 } } }, "UnityEnvironment.step": { "total": 0.03861313200002314, "count": 1, "is_parallel": true, "self": 0.0006142269999145356, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004966480000803131, "count": 1, "is_parallel": true, "self": 0.0004966480000803131 }, "communicator.exchange": { "total": 0.035568646000001536, "count": 1, "is_parallel": true, "self": 0.035568646000001536 }, "steps_from_proto": { "total": 0.0019336110000267581, "count": 1, "is_parallel": true, "self": 0.0004045139997970182, "children": { "_process_rank_one_or_two_observation": { "total": 0.00152909700022974, "count": 10, "is_parallel": true, "self": 0.00152909700022974 } } } } } } }, "UnityEnvironment.step": { "total": 238.02169214999788, "count": 18191, "is_parallel": true, "self": 11.096550790992865, "children": { "UnityEnvironment._generate_step_input": { "total": 5.850648131997673, "count": 18191, "is_parallel": true, "self": 5.850648131997673 }, "communicator.exchange": { "total": 181.19132492800838, "count": 18191, "is_parallel": true, "self": 181.19132492800838 }, "steps_from_proto": { "total": 39.88316829899895, "count": 18191, "is_parallel": true, "self": 6.918729219982538, "children": { "_process_rank_one_or_two_observation": { "total": 32.964439079016415, "count": 181910, "is_parallel": true, "self": 32.964439079016415 } } } } } } } } } } }, "trainer_advance": { "total": 133.73663762900367, "count": 18192, "self": 0.4488158969984397, "children": { "process_trajectory": { "total": 29.14393808100533, "count": 18192, "self": 28.655171231005284, "children": { "RLTrainer._checkpoint": { "total": 0.48876685000004727, "count": 4, "self": 0.48876685000004727 } } }, "_update_policy": { "total": 104.1438836509999, "count": 90, "self": 42.03109385399728, "children": { "TorchPPOOptimizer.update": { "total": 62.11278979700262, "count": 4587, "self": 62.11278979700262 } } } } } } }, "trainer_threads": { "total": 9.93999947240809e-07, "count": 1, "self": 9.93999947240809e-07 }, "TrainerController._save_models": { "total": 0.08220679000010023, "count": 1, "self": 0.000773247000097399, "children": { "RLTrainer._checkpoint": { "total": 0.08143354300000283, "count": 1, "self": 0.08143354300000283 } } } } } } }