{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0314401388168335, "min": 1.0051497220993042, "max": 2.867361545562744, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9859.5361328125, "min": 9859.5361328125, "max": 29459.2734375, "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": 12.99124813079834, "min": 0.3702958822250366, "max": 12.99124813079834, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.29345703125, "min": 71.83740234375, "max": 2619.03955078125, "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": 0.0614592554572714, "min": 0.0614592554572714, "max": 0.07415595181770258, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2458370218290856, "min": 0.2458370218290856, "max": 0.3707797590885129, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19423531740903854, "min": 0.09608684335241788, "max": 0.32164572004009695, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7769412696361542, "min": 0.3843473734096715, "max": 1.6082286002004849, "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": 25.34090909090909, "min": 2.8863636363636362, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 127.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 2.8863636363636362, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 127.0, "max": 1399.0, "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": "1722302830", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTaget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722303511" }, "total": 680.6548186059999, "count": 1, "self": 0.5887249320001047, "children": { "run_training.setup": { "total": 0.08641272399995614, "count": 1, "self": 0.08641272399995614 }, "TrainerController.start_learning": { "total": 679.9796809499999, "count": 1, "self": 1.0792689660269161, "children": { "TrainerController._reset_env": { "total": 3.63936769299994, "count": 1, "self": 3.63936769299994 }, "TrainerController.advance": { "total": 675.159223189973, "count": 18202, "self": 0.5155836089709283, "children": { "env_step": { "total": 674.643639581002, "count": 18202, "self": 523.3787212800371, "children": { "SubprocessEnvManager._take_step": { "total": 150.7501480359947, "count": 18202, "self": 3.2548000069772343, "children": { "TorchPolicy.evaluate": { "total": 147.49534802901746, "count": 18202, "self": 147.49534802901746 } } }, "workers": { "total": 0.5147702649702524, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 677.2934265279858, "count": 18202, "is_parallel": true, "self": 314.62748886996235, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007443749999993088, "count": 1, "is_parallel": true, "self": 0.005432401000007303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020113489999857848, "count": 10, "is_parallel": true, "self": 0.0020113489999857848 } } }, "UnityEnvironment.step": { "total": 0.0559811930000933, "count": 1, "is_parallel": true, "self": 0.0009678750001285152, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004953979999982039, "count": 1, "is_parallel": true, "self": 0.0004953979999982039 }, "communicator.exchange": { "total": 0.051786097999979575, "count": 1, "is_parallel": true, "self": 0.051786097999979575 }, "steps_from_proto": { "total": 0.0027318219999870053, "count": 1, "is_parallel": true, "self": 0.0005438100001811108, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021880119998058944, "count": 10, "is_parallel": true, "self": 0.0021880119998058944 } } } } } } }, "UnityEnvironment.step": { "total": 362.6659376580235, "count": 18201, "is_parallel": true, "self": 18.06370439600539, "children": { "UnityEnvironment._generate_step_input": { "total": 8.837192586006609, "count": 18201, "is_parallel": true, "self": 8.837192586006609 }, "communicator.exchange": { "total": 285.70931507501314, "count": 18201, "is_parallel": true, "self": 285.70931507501314 }, "steps_from_proto": { "total": 50.05572560099836, "count": 18201, "is_parallel": true, "self": 10.646592299007011, "children": { "_process_rank_one_or_two_observation": { "total": 39.409133301991346, "count": 182010, "is_parallel": true, "self": 39.409133301991346 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020649799989769235, "count": 1, "self": 0.00020649799989769235, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 667.0517961679486, "count": 897730, "is_parallel": true, "self": 21.436800353922195, "children": { "process_trajectory": { "total": 367.3015639110264, "count": 897730, "is_parallel": true, "self": 366.4662908690267, "children": { "RLTrainer._checkpoint": { "total": 0.8352730419996988, "count": 4, "is_parallel": true, "self": 0.8352730419996988 } } }, "_update_policy": { "total": 278.31343190300004, "count": 90, "is_parallel": true, "self": 78.18999998699917, "children": { "TorchPPOOptimizer.update": { "total": 200.12343191600087, "count": 4587, "is_parallel": true, "self": 200.12343191600087 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10161460300014369, "count": 1, "self": 0.0015986600001269835, "children": { "RLTrainer._checkpoint": { "total": 0.1000159430000167, "count": 1, "self": 0.1000159430000167 } } } } } } }