{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0073847770690918, "min": 1.0073847770690918, "max": 2.869391918182373, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9618.509765625, "min": 9618.509765625, "max": 29511.6953125, "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": 12.92364501953125, "min": 0.4203534424304962, "max": 12.92364501953125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.11083984375, "min": 81.54856872558594, "max": 2600.67529296875, "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.Losses.PolicyLoss.mean": { "value": 0.06752405896537204, "min": 0.0613302391442452, "max": 0.07585467540843906, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2700962358614882, "min": 0.24637888823011, "max": 0.37927337704219527, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18335537868095378, "min": 0.11157853680311282, "max": 0.2784056130577536, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7334215147238151, "min": 0.4463141472124513, "max": 1.392028065288768, "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.CumulativeReward.mean": { "value": 25.5, "min": 3.1136363636363638, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 137.0, "max": 1382.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 3.1136363636363638, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 137.0, "max": 1382.0, "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": "1710720550", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn config/ppo/SnowballTarget.yaml --env=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1710721003" }, "total": 453.157263996, "count": 1, "self": 0.48685632000001533, "children": { "run_training.setup": { "total": 0.0977737220000563, "count": 1, "self": 0.0977737220000563 }, "TrainerController.start_learning": { "total": 452.5726339539999, "count": 1, "self": 0.563337746002162, "children": { "TrainerController._reset_env": { "total": 2.6488502309998694, "count": 1, "self": 2.6488502309998694 }, "TrainerController.advance": { "total": 449.265864462998, "count": 18199, "self": 0.25376810499392377, "children": { "env_step": { "total": 449.0120963580041, "count": 18199, "self": 288.7399781059951, "children": { "SubprocessEnvManager._take_step": { "total": 160.0035336159956, "count": 18199, "self": 1.48299022999322, "children": { "TorchPolicy.evaluate": { "total": 158.52054338600237, "count": 18199, "self": 158.52054338600237 } } }, "workers": { "total": 0.2685846360134292, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 451.469805042997, "count": 18199, "is_parallel": true, "self": 226.67311498098888, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021300020000580844, "count": 1, "is_parallel": true, "self": 0.0006196130004809675, "children": { "_process_rank_one_or_two_observation": { "total": 0.001510388999577117, "count": 10, "is_parallel": true, "self": 0.001510388999577117 } } }, "UnityEnvironment.step": { "total": 0.0509764799999175, "count": 1, "is_parallel": true, "self": 0.0006289379998634104, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042212200014546397, "count": 1, "is_parallel": true, "self": 0.00042212200014546397 }, "communicator.exchange": { "total": 0.042883909000011045, "count": 1, "is_parallel": true, "self": 0.042883909000011045 }, "steps_from_proto": { "total": 0.007041510999897582, "count": 1, "is_parallel": true, "self": 0.0003837510002995259, "children": { "_process_rank_one_or_two_observation": { "total": 0.006657759999598056, "count": 10, "is_parallel": true, "self": 0.006657759999598056 } } } } } } }, "UnityEnvironment.step": { "total": 224.7966900620081, "count": 18198, "is_parallel": true, "self": 10.600683241970955, "children": { "UnityEnvironment._generate_step_input": { "total": 5.263074710011551, "count": 18198, "is_parallel": true, "self": 5.263074710011551 }, "communicator.exchange": { "total": 172.23376768702633, "count": 18198, "is_parallel": true, "self": 172.23376768702633 }, "steps_from_proto": { "total": 36.699164422999274, "count": 18198, "is_parallel": true, "self": 6.609555538010454, "children": { "_process_rank_one_or_two_observation": { "total": 30.08960888498882, "count": 181980, "is_parallel": true, "self": 30.08960888498882 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013547499997912382, "count": 1, "self": 0.00013547499997912382, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.9665945880288, "count": 671735, "is_parallel": true, "self": 13.799363970980721, "children": { "process_trajectory": { "total": 239.24324325604675, "count": 671735, "is_parallel": true, "self": 238.724867879047, "children": { "RLTrainer._checkpoint": { "total": 0.5183753769997566, "count": 4, "is_parallel": true, "self": 0.5183753769997566 } } }, "_update_policy": { "total": 190.9239873610013, "count": 90, "is_parallel": true, "self": 66.24304477299756, "children": { "TorchPPOOptimizer.update": { "total": 124.68094258800375, "count": 4587, "is_parallel": true, "self": 124.68094258800375 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09444603899987669, "count": 1, "self": 0.001175983999928576, "children": { "RLTrainer._checkpoint": { "total": 0.09327005499994812, "count": 1, "self": 0.09327005499994812 } } } } } } }