{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.4029814004898071, "min": 1.4029814004898071, "max": 2.8775932788848877, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14414.2314453125, "min": 13610.66015625, "max": 29501.0859375, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 10.636680603027344, "min": 0.21429063379764557, "max": 10.636680603027344, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2180.51953125, "min": 41.572383880615234, "max": 2180.51953125, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04811769659718266, "min": 0.04104742056321507, "max": 0.05156516316492343, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2405884829859133, "min": 0.16639067826084403, "max": 0.2463710664936419, "count": 15 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2576294199874004, "min": 0.09393358548792699, "max": 0.29672235858937107, "count": 15 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.288147099937002, "min": 0.37573434195170796, "max": 1.4836117929468553, "count": 15 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.776096741333334e-06, "min": 9.776096741333334e-06, "max": 0.000289176003608, "count": 15 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.888048370666667e-05, "min": 4.888048370666667e-05, "max": 0.0013468800510399999, "count": 15 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10325866666666668, "min": 0.10325866666666668, "max": 0.196392, "count": 15 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5162933333333334, "min": 0.4394346666666667, "max": 0.94896, "count": 15 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00017260746666666673, "min": 0.00017260746666666673, "max": 0.0048199608, "count": 15 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008630373333333337, "min": 0.0008630373333333337, "max": 0.022453104, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 21.072727272727274, "min": 2.727272727272727, "max": 21.568181818181817, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1159.0, "min": 120.0, "max": 1159.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.072727272727274, "min": 2.727272727272727, "max": 21.568181818181817, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1159.0, "min": 120.0, "max": 1159.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678861699", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678862046" }, "total": 347.09764913600003, "count": 1, "self": 0.4811627600000179, "children": { "run_training.setup": { "total": 0.10372786699997505, "count": 1, "self": 0.10372786699997505 }, "TrainerController.start_learning": { "total": 346.51275850900004, "count": 1, "self": 0.45498973699909584, "children": { "TrainerController._reset_env": { "total": 9.468434535000029, "count": 1, "self": 9.468434535000029 }, "TrainerController.advance": { "total": 336.44021897100095, "count": 13671, "self": 0.22073704800112637, "children": { "env_step": { "total": 336.2194819229998, "count": 13671, "self": 232.2554846059889, "children": { "SubprocessEnvManager._take_step": { "total": 103.74587339600549, "count": 13671, "self": 1.9057289219979907, "children": { "TorchPolicy.evaluate": { "total": 101.8401444740075, "count": 13671, "self": 101.8401444740075 } } }, "workers": { "total": 0.21812392100542866, "count": 13671, "self": 0.0, "children": { "worker_root": { "total": 345.422125693996, "count": 13671, "is_parallel": true, "self": 158.76117911999165, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005889721000016834, "count": 1, "is_parallel": true, "self": 0.004355717999999342, "children": { "_process_rank_one_or_two_observation": { "total": 0.001534003000017492, "count": 10, "is_parallel": true, "self": 0.001534003000017492 } } }, "UnityEnvironment.step": { "total": 0.10411112900004582, "count": 1, "is_parallel": true, "self": 0.0006587380000837584, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043666299995948066, "count": 1, "is_parallel": true, "self": 0.00043666299995948066 }, "communicator.exchange": { "total": 0.09578287699997645, "count": 1, "is_parallel": true, "self": 0.09578287699997645 }, "steps_from_proto": { "total": 0.00723285100002613, "count": 1, "is_parallel": true, "self": 0.0004365299999449235, "children": { "_process_rank_one_or_two_observation": { "total": 0.006796321000081207, "count": 10, "is_parallel": true, "self": 0.006796321000081207 } } } } } } }, "UnityEnvironment.step": { "total": 186.66094657400436, "count": 13670, "is_parallel": true, "self": 7.350952437029775, "children": { "UnityEnvironment._generate_step_input": { "total": 3.910758274988382, "count": 13670, "is_parallel": true, "self": 3.910758274988382 }, "communicator.exchange": { "total": 151.92336851499323, "count": 13670, "is_parallel": true, "self": 151.92336851499323 }, "steps_from_proto": { "total": 23.47586734699297, "count": 13670, "is_parallel": true, "self": 4.684665202995404, "children": { "_process_rank_one_or_two_observation": { "total": 18.791202143997566, "count": 136700, "is_parallel": true, "self": 18.791202143997566 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022439099996063305, "count": 1, "self": 0.00022439099996063305, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 333.92899737207074, "count": 310507, "is_parallel": true, "self": 7.498132101096473, "children": { "process_trajectory": { "total": 198.93047171497392, "count": 310507, "is_parallel": true, "self": 198.3898199509739, "children": { "RLTrainer._checkpoint": { "total": 0.5406517640000175, "count": 3, "is_parallel": true, "self": 0.5406517640000175 } } }, "_update_policy": { "total": 127.50039355600035, "count": 68, "is_parallel": true, "self": 58.96786243100172, "children": { "TorchPPOOptimizer.update": { "total": 68.53253112499863, "count": 1632, "is_parallel": true, "self": 68.53253112499863 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14889087500000642, "count": 1, "self": 0.0008760370000118201, "children": { "RLTrainer._checkpoint": { "total": 0.1480148379999946, "count": 1, "self": 0.1480148379999946 } } } } } } }