{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.051292061805725, "min": 1.046040415763855, "max": 2.872748613357544, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10141.814453125, "min": 10141.814453125, "max": 29451.419921875, "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": 12.810480117797852, "min": 0.35618507862091064, "max": 12.810480117797852, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2498.043701171875, "min": 69.09990692138672, "max": 2579.677734375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06877257443678295, "min": 0.0627427321870688, "max": 0.07253669785588464, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2750902977471318, "min": 0.2509709287482752, "max": 0.3527991427239898, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20437291527495666, "min": 0.11878736371484895, "max": 0.26286844336519055, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8174916610998266, "min": 0.4751494548593958, "max": 1.3143422168259526, "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": 25.59090909090909, "min": 3.4318181818181817, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 151.0, "max": 1384.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.4318181818181817, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 151.0, "max": 1384.0, "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": "1700123389", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700123860" }, "total": 470.96633005399997, "count": 1, "self": 0.6931804789999774, "children": { "run_training.setup": { "total": 0.07214436700002125, "count": 1, "self": 0.07214436700002125 }, "TrainerController.start_learning": { "total": 470.20100520799997, "count": 1, "self": 0.5608526920017312, "children": { "TrainerController._reset_env": { "total": 9.130438507999997, "count": 1, "self": 9.130438507999997 }, "TrainerController.advance": { "total": 460.3811510689983, "count": 18224, "self": 0.2649098269935166, "children": { "env_step": { "total": 460.1162412420048, "count": 18224, "self": 315.68445208999555, "children": { "SubprocessEnvManager._take_step": { "total": 144.161032027008, "count": 18224, "self": 1.4066545990081067, "children": { "TorchPolicy.evaluate": { "total": 142.75437742799988, "count": 18224, "self": 142.75437742799988 } } }, "workers": { "total": 0.2707571250012393, "count": 18224, "self": 0.0, "children": { "worker_root": { "total": 468.917822564, "count": 18224, "is_parallel": true, "self": 232.03114525800373, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006033474999981081, "count": 1, "is_parallel": true, "self": 0.004027396999845223, "children": { "_process_rank_one_or_two_observation": { "total": 0.002006078000135858, "count": 10, "is_parallel": true, "self": 0.002006078000135858 } } }, "UnityEnvironment.step": { "total": 0.03716382700002896, "count": 1, "is_parallel": true, "self": 0.0007409709999706138, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029355700002042795, "count": 1, "is_parallel": true, "self": 0.00029355700002042795 }, "communicator.exchange": { "total": 0.03379844900001672, "count": 1, "is_parallel": true, "self": 0.03379844900001672 }, "steps_from_proto": { "total": 0.0023308500000212007, "count": 1, "is_parallel": true, "self": 0.0005625000001145963, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017683499999066044, "count": 10, "is_parallel": true, "self": 0.0017683499999066044 } } } } } } }, "UnityEnvironment.step": { "total": 236.88667730599627, "count": 18223, "is_parallel": true, "self": 10.392620052005952, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2897849799990695, "count": 18223, "is_parallel": true, "self": 5.2897849799990695 }, "communicator.exchange": { "total": 188.29452540300065, "count": 18223, "is_parallel": true, "self": 188.29452540300065 }, "steps_from_proto": { "total": 32.9097468709906, "count": 18223, "is_parallel": true, "self": 6.148711163985979, "children": { "_process_rank_one_or_two_observation": { "total": 26.761035707004623, "count": 182230, "is_parallel": true, "self": 26.761035707004623 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014903499993579317, "count": 1, "self": 0.00014903499993579317, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.670109687997, "count": 487445, "is_parallel": true, "self": 9.990653781034382, "children": { "process_trajectory": { "total": 253.32336415396247, "count": 487445, "is_parallel": true, "self": 252.45327061096253, "children": { "RLTrainer._checkpoint": { "total": 0.870093542999939, "count": 4, "is_parallel": true, "self": 0.870093542999939 } } }, "_update_policy": { "total": 193.35609175300016, "count": 90, "is_parallel": true, "self": 66.99237321599827, "children": { "TorchPPOOptimizer.update": { "total": 126.36371853700189, "count": 4587, "is_parallel": true, "self": 126.36371853700189 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12841390400001274, "count": 1, "self": 0.0012584049999304625, "children": { "RLTrainer._checkpoint": { "total": 0.12715549900008227, "count": 1, "self": 0.12715549900008227 } } } } } } }