{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7945277690887451, "min": 0.7945277690887451, "max": 2.8587188720703125, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7586.1513671875, "min": 7586.1513671875, "max": 29307.5859375, "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": 13.168272018432617, "min": 0.34102368354797363, "max": 13.168272018432617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2567.81298828125, "min": 66.1585922241211, "max": 2673.463623046875, "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": 0.07241338226623495, "min": 0.06235784397804488, "max": 0.07311035049474324, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2896535290649398, "min": 0.2494313759121795, "max": 0.3655517524737162, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19191494752086843, "min": 0.11354467662179148, "max": 0.30274705103799404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7676597900834737, "min": 0.4541787064871659, "max": 1.5137352551899703, "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": 25.522727272727273, "min": 3.090909090909091, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 136.0, "max": 1427.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.090909090909091, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 136.0, "max": 1427.0, "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": "1707639669", "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=./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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707640103" }, "total": 433.35343815399995, "count": 1, "self": 0.426371432999872, "children": { "run_training.setup": { "total": 0.04948742700003095, "count": 1, "self": 0.04948742700003095 }, "TrainerController.start_learning": { "total": 432.87757929400004, "count": 1, "self": 0.5383631769922204, "children": { "TrainerController._reset_env": { "total": 3.771140962000004, "count": 1, "self": 3.771140962000004 }, "TrainerController.advance": { "total": 428.47413212100787, "count": 18199, "self": 0.25004255101862327, "children": { "env_step": { "total": 428.22408956998925, "count": 18199, "self": 278.400575802979, "children": { "SubprocessEnvManager._take_step": { "total": 149.55717883000568, "count": 18199, "self": 1.420347408006137, "children": { "TorchPolicy.evaluate": { "total": 148.13683142199955, "count": 18199, "self": 148.13683142199955 } } }, "workers": { "total": 0.266334937004558, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 431.81501716700427, "count": 18199, "is_parallel": true, "self": 215.30535988299278, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00620952600002056, "count": 1, "is_parallel": true, "self": 0.0047324110000772635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014771149999432964, "count": 10, "is_parallel": true, "self": 0.0014771149999432964 } } }, "UnityEnvironment.step": { "total": 0.036022082000044975, "count": 1, "is_parallel": true, "self": 0.0008672569999816915, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041549000002305547, "count": 1, "is_parallel": true, "self": 0.00041549000002305547 }, "communicator.exchange": { "total": 0.032746697999982644, "count": 1, "is_parallel": true, "self": 0.032746697999982644 }, "steps_from_proto": { "total": 0.0019926370000575844, "count": 1, "is_parallel": true, "self": 0.00039673000014772697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015959069999098574, "count": 10, "is_parallel": true, "self": 0.0015959069999098574 } } } } } } }, "UnityEnvironment.step": { "total": 216.5096572840115, "count": 18198, "is_parallel": true, "self": 10.42615886100566, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3869512640030734, "count": 18198, "is_parallel": true, "self": 5.3869512640030734 }, "communicator.exchange": { "total": 167.64475050799876, "count": 18198, "is_parallel": true, "self": 167.64475050799876 }, "steps_from_proto": { "total": 33.051796651004, "count": 18198, "is_parallel": true, "self": 6.04247532900024, "children": { "_process_rank_one_or_two_observation": { "total": 27.009321322003757, "count": 181980, "is_parallel": true, "self": 27.009321322003757 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017670199997610325, "count": 1, "self": 0.00017670199997610325, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 423.0315505759635, "count": 654588, "is_parallel": true, "self": 13.86601326296227, "children": { "process_trajectory": { "total": 232.55934040200145, "count": 654588, "is_parallel": true, "self": 232.05074106200152, "children": { "RLTrainer._checkpoint": { "total": 0.5085993399999325, "count": 4, "is_parallel": true, "self": 0.5085993399999325 } } }, "_update_policy": { "total": 176.60619691099976, "count": 90, "is_parallel": true, "self": 54.72874049300435, "children": { "TorchPPOOptimizer.update": { "total": 121.8774564179954, "count": 4587, "is_parallel": true, "self": 121.8774564179954 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09376633199997286, "count": 1, "self": 0.0010438780000185943, "children": { "RLTrainer._checkpoint": { "total": 0.09272245399995427, "count": 1, "self": 0.09272245399995427 } } } } } } }