{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0051778554916382, "min": 1.0051778554916382, "max": 2.850841760635376, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9608.4951171875, "min": 9608.4951171875, "max": 29258.189453125, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.010763168334961, "min": 0.4187123775482178, "max": 13.010763168334961, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2524.088134765625, "min": 81.2302017211914, "max": 2651.8447265625, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06841872785954882, "min": 0.06083166407576451, "max": 0.07478306438207774, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2736749114381953, "min": 0.26513361569274874, "max": 0.3739153219103887, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21629036736546778, "min": 0.1329953646590915, "max": 0.2844530167971171, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8651614694618711, "min": 0.531981458636366, "max": 1.4132217963536582, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.362658084800001e-06, "min": 5.362658084800001e-06, "max": 0.0002739385621648, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.1450632339200004e-05, "min": 2.1450632339200004e-05, "max": 0.0013142528306239998, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10210672, "min": 0.10210672, "max": 0.20761871999999995, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40842688, "min": 0.40842688, "max": 1.0163136, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000002, "min": 0.00010556848000000002, "max": 0.004891976480000001, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004222739200000001, "min": 0.0004222739200000001, "max": 0.023471862399999998, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.59090909090909, "min": 3.8181818181818183, "max": 25.78181818181818, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 168.0, "max": 1418.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.8181818181818183, "max": 25.78181818181818, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 168.0, "max": 1418.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680788900", "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": "1680789526" }, "total": 625.8838122110001, "count": 1, "self": 0.7380752690000918, "children": { "run_training.setup": { "total": 0.20117395799996984, "count": 1, "self": 0.20117395799996984 }, "TrainerController.start_learning": { "total": 624.944562984, "count": 1, "self": 0.8224402120023342, "children": { "TrainerController._reset_env": { "total": 4.503825919000008, "count": 1, "self": 4.503825919000008 }, "TrainerController.advance": { "total": 619.3904230329975, "count": 22750, "self": 0.4076515319976579, "children": { "env_step": { "total": 618.9827715009999, "count": 22750, "self": 451.3973156260016, "children": { "SubprocessEnvManager._take_step": { "total": 167.18324239599485, "count": 22750, "self": 2.437499054995442, "children": { "TorchPolicy.evaluate": { "total": 164.7457433409994, "count": 22750, "self": 164.7457433409994 } } }, "workers": { "total": 0.4022134790034215, "count": 22750, "self": 0.0, "children": { "worker_root": { "total": 622.7321380549978, "count": 22750, "is_parallel": true, "self": 288.29527991399027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007069178000051579, "count": 1, "is_parallel": true, "self": 0.004372646000035729, "children": { "_process_rank_one_or_two_observation": { "total": 0.00269653200001585, "count": 10, "is_parallel": true, "self": 0.00269653200001585 } } }, "UnityEnvironment.step": { "total": 0.04195419900003117, "count": 1, "is_parallel": true, "self": 0.0006739550000816052, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048259299995834226, "count": 1, "is_parallel": true, "self": 0.00048259299995834226 }, "communicator.exchange": { "total": 0.03878601899998557, "count": 1, "is_parallel": true, "self": 0.03878601899998557 }, "steps_from_proto": { "total": 0.0020116320000056476, "count": 1, "is_parallel": true, "self": 0.0004222539999432229, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015893780000624247, "count": 10, "is_parallel": true, "self": 0.0015893780000624247 } } } } } } }, "UnityEnvironment.step": { "total": 334.4368581410075, "count": 22749, "is_parallel": true, "self": 13.594683386995769, "children": { "UnityEnvironment._generate_step_input": { "total": 7.380644005000818, "count": 22749, "is_parallel": true, "self": 7.380644005000818 }, "communicator.exchange": { "total": 268.66307402399747, "count": 22749, "is_parallel": true, "self": 268.66307402399747 }, "steps_from_proto": { "total": 44.798456725013466, "count": 22749, "is_parallel": true, "self": 9.178264315028798, "children": { "_process_rank_one_or_two_observation": { "total": 35.62019240998467, "count": 227490, "is_parallel": true, "self": 35.62019240998467 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011838300008548686, "count": 1, "self": 0.00011838300008548686, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 614.3522099160016, "count": 556875, "is_parallel": true, "self": 14.464264445007757, "children": { "process_trajectory": { "total": 339.1460279739942, "count": 556875, "is_parallel": true, "self": 337.2234935659942, "children": { "RLTrainer._checkpoint": { "total": 1.92253440799999, "count": 5, "is_parallel": true, "self": 1.92253440799999 } } }, "_update_policy": { "total": 260.74191749699963, "count": 113, "is_parallel": true, "self": 98.25234598400107, "children": { "TorchPPOOptimizer.update": { "total": 162.48957151299857, "count": 5760, "is_parallel": true, "self": 162.48957151299857 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22775543700004164, "count": 1, "self": 0.0011918860001287612, "children": { "RLTrainer._checkpoint": { "total": 0.22656355099991288, "count": 1, "self": 0.22656355099991288 } } } } } } }