{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7912644147872925, "min": 0.7912644147872925, "max": 2.848909854888916, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7520.17724609375, "min": 7520.17724609375, "max": 29081.671875, "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": 12.700643539428711, "min": 0.31351229548454285, "max": 12.780616760253906, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2476.62548828125, "min": 60.82138442993164, "max": 2607.245849609375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06620399273236341, "min": 0.06373375403505348, "max": 0.07979390239480007, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26481597092945364, "min": 0.255748686610519, "max": 0.3989695119740003, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20809092891274714, "min": 0.128333456314388, "max": 0.29421647491992686, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8323637156509885, "min": 0.513333825257552, "max": 1.3508812942925623, "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": 24.863636363636363, "min": 3.840909090909091, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1094.0, "min": 169.0, "max": 1377.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.863636363636363, "min": 3.840909090909091, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1094.0, "min": 169.0, "max": 1377.0, "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": "1748413663", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748414099" }, "total": 435.761787134, "count": 1, "self": 0.4507207160000348, "children": { "run_training.setup": { "total": 0.02377608599999803, "count": 1, "self": 0.02377608599999803 }, "TrainerController.start_learning": { "total": 435.28729033199994, "count": 1, "self": 0.3576598929988677, "children": { "TrainerController._reset_env": { "total": 3.438752730000033, "count": 1, "self": 3.438752730000033 }, "TrainerController.advance": { "total": 431.40340782000095, "count": 18192, "self": 0.3811303830057682, "children": { "env_step": { "total": 308.4741641409927, "count": 18192, "self": 234.25354143298318, "children": { "SubprocessEnvManager._take_step": { "total": 74.00434006199976, "count": 18192, "self": 1.2936236739948868, "children": { "TorchPolicy.evaluate": { "total": 72.71071638800487, "count": 18192, "self": 72.71071638800487 } } }, "workers": { "total": 0.2162826460097449, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 433.858644852006, "count": 18192, "is_parallel": true, "self": 228.16035188701102, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004970676999960233, "count": 1, "is_parallel": true, "self": 0.0034526249999089487, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015180520000512843, "count": 10, "is_parallel": true, "self": 0.0015180520000512843 } } }, "UnityEnvironment.step": { "total": 0.03769761099999869, "count": 1, "is_parallel": true, "self": 0.0005851000000234308, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037954099997250523, "count": 1, "is_parallel": true, "self": 0.00037954099997250523 }, "communicator.exchange": { "total": 0.03493108200001416, "count": 1, "is_parallel": true, "self": 0.03493108200001416 }, "steps_from_proto": { "total": 0.001801887999988594, "count": 1, "is_parallel": true, "self": 0.000369883000075788, "children": { "_process_rank_one_or_two_observation": { "total": 0.001432004999912806, "count": 10, "is_parallel": true, "self": 0.001432004999912806 } } } } } } }, "UnityEnvironment.step": { "total": 205.698292964995, "count": 18191, "is_parallel": true, "self": 9.858616713993797, "children": { "UnityEnvironment._generate_step_input": { "total": 5.460354319994963, "count": 18191, "is_parallel": true, "self": 5.460354319994963 }, "communicator.exchange": { "total": 157.9193196410098, "count": 18191, "is_parallel": true, "self": 157.9193196410098 }, "steps_from_proto": { "total": 32.46000228999645, "count": 18191, "is_parallel": true, "self": 5.891197719979459, "children": { "_process_rank_one_or_two_observation": { "total": 26.568804570016994, "count": 181910, "is_parallel": true, "self": 26.568804570016994 } } } } } } } } } } }, "trainer_advance": { "total": 122.5481132960025, "count": 18192, "self": 0.4289633400027242, "children": { "process_trajectory": { "total": 27.82905246700045, "count": 18192, "self": 27.36701852900046, "children": { "RLTrainer._checkpoint": { "total": 0.4620339379999905, "count": 4, "self": 0.4620339379999905 } } }, "_update_policy": { "total": 94.29009748899932, "count": 90, "self": 37.82047541800273, "children": { "TorchPPOOptimizer.update": { "total": 56.46962207099659, "count": 4587, "self": 56.46962207099659 } } } } } } }, "trainer_threads": { "total": 7.880000794102671e-07, "count": 1, "self": 7.880000794102671e-07 }, "TrainerController._save_models": { "total": 0.0874691010000106, "count": 1, "self": 0.0010178720000340036, "children": { "RLTrainer._checkpoint": { "total": 0.08645122899997659, "count": 1, "self": 0.08645122899997659 } } } } } } }