{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9707475900650024, "min": 0.9707475900650024, "max": 2.8541529178619385, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9290.0546875, "min": 9290.0546875, "max": 29292.171875, "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": 11.677877426147461, "min": 0.352594792842865, "max": 11.677877426147461, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2277.18603515625, "min": 68.40338897705078, "max": 2340.248291015625, "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": 0.06800448360844907, "min": 0.060132639760858565, "max": 0.07485666880993269, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2720179344337963, "min": 0.2654119311990536, "max": 0.3733510146004275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1861837363491456, "min": 0.12084910791257725, "max": 0.28798139884191404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7447349453965824, "min": 0.483396431650309, "max": 1.4399069942095701, "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": 23.295454545454547, "min": 3.1136363636363638, "max": 23.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1025.0, "min": 137.0, "max": 1295.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.295454545454547, "min": 3.1136363636363638, "max": 23.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1025.0, "min": 137.0, "max": 1295.0, "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": "1679366406", "python_version": "3.9.9 | packaged by conda-forge | (main, Dec 20 2021, 02:40:17) \n[GCC 9.4.0]", "command_line_arguments": "/home/qiang/opt/miniconda3/envs/x-hf-deeprl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.19.5", "end_time_seconds": "1679366750" }, "total": 344.1936590319965, "count": 1, "self": 0.2701337659964338, "children": { "run_training.setup": { "total": 0.017836565035395324, "count": 1, "self": 0.017836565035395324 }, "TrainerController.start_learning": { "total": 343.9056887009647, "count": 1, "self": 0.48486046004109085, "children": { "TrainerController._reset_env": { "total": 2.706846870947629, "count": 1, "self": 2.706846870947629 }, "TrainerController.advance": { "total": 340.5939005269902, "count": 18205, "self": 0.23664178582839668, "children": { "env_step": { "total": 340.3572587411618, "count": 18205, "self": 228.6260609314777, "children": { "SubprocessEnvManager._take_step": { "total": 111.49802704702597, "count": 18205, "self": 1.0811855671927333, "children": { "TorchPolicy.evaluate": { "total": 110.41684147983324, "count": 18205, "self": 21.6761242414359, "children": { "TorchPolicy.sample_actions": { "total": 88.74071723839734, "count": 18205, "self": 88.74071723839734 } } } } }, "workers": { "total": 0.2331707626581192, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 343.2008094689809, "count": 18205, "is_parallel": true, "self": 182.4128531573806, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018118569860234857, "count": 1, "is_parallel": true, "self": 0.00043383287265896797, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013780241133645177, "count": 10, "is_parallel": true, "self": 0.0013780241133645177 } } }, "UnityEnvironment.step": { "total": 0.02287243597675115, "count": 1, "is_parallel": true, "self": 0.0004944339161738753, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003357550594955683, "count": 1, "is_parallel": true, "self": 0.0003357550594955683 }, "communicator.exchange": { "total": 0.01946852495893836, "count": 1, "is_parallel": true, "self": 0.01946852495893836 }, "steps_from_proto": { "total": 0.002573722042143345, "count": 1, "is_parallel": true, "self": 0.0003368080360814929, "children": { "_process_rank_one_or_two_observation": { "total": 0.002236914006061852, "count": 10, "is_parallel": true, "self": 0.002236914006061852 } } } } } } }, "UnityEnvironment.step": { "total": 160.78795631160028, "count": 18204, "is_parallel": true, "self": 5.772694329032674, "children": { "UnityEnvironment._generate_step_input": { "total": 3.728552536922507, "count": 18204, "is_parallel": true, "self": 3.728552536922507 }, "communicator.exchange": { "total": 120.63420363864861, "count": 18204, "is_parallel": true, "self": 120.63420363864861 }, "steps_from_proto": { "total": 30.652505806996487, "count": 18204, "is_parallel": true, "self": 4.729406311758794, "children": { "_process_rank_one_or_two_observation": { "total": 25.923099495237693, "count": 182040, "is_parallel": true, "self": 25.923099495237693 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010161299724131823, "count": 1, "self": 0.00010161299724131823, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 339.7048151703784, "count": 228530, "is_parallel": true, "self": 3.4699792126193643, "children": { "process_trajectory": { "total": 181.77121722546872, "count": 228530, "is_parallel": true, "self": 181.04588336439338, "children": { "RLTrainer._checkpoint": { "total": 0.7253338610753417, "count": 4, "is_parallel": true, "self": 0.7253338610753417 } } }, "_update_policy": { "total": 154.46361873229034, "count": 90, "is_parallel": true, "self": 47.57346931716893, "children": { "TorchPPOOptimizer.update": { "total": 106.89014941512141, "count": 4587, "is_parallel": true, "self": 106.89014941512141 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11997922998853028, "count": 1, "self": 0.0008895969949662685, "children": { "RLTrainer._checkpoint": { "total": 0.11908963299356401, "count": 1, "self": 0.11908963299356401 } } } } } } }