{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0332295894622803, "min": 1.0332295894622803, "max": 2.8615000247955322, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9933.4697265625, "min": 9933.4697265625, "max": 29367.57421875, "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": 12.445021629333496, "min": 0.39798519015312195, "max": 12.445021629333496, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2426.779296875, "min": 77.2091293334961, "max": 2528.49365234375, "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": 0.06956447699385714, "min": 0.06210766846142731, "max": 0.07464576551174819, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27825790797542854, "min": 0.2654585246060628, "max": 0.3732288275587409, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2278921677931851, "min": 0.14053384746954428, "max": 0.28311064956234955, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9115686711727404, "min": 0.5621353898781771, "max": 1.4155532478117476, "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": 23.954545454545453, "min": 3.75, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1054.0, "min": 165.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.954545454545453, "min": 3.75, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1054.0, "min": 165.0, "max": 1370.0, "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": "1685325870", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685326327" }, "total": 457.69558619199995, "count": 1, "self": 0.6865333999999166, "children": { "run_training.setup": { "total": 0.0701670409999906, "count": 1, "self": 0.0701670409999906 }, "TrainerController.start_learning": { "total": 456.93888575100004, "count": 1, "self": 0.5216198539966399, "children": { "TrainerController._reset_env": { "total": 4.052331103000029, "count": 1, "self": 4.052331103000029 }, "TrainerController.advance": { "total": 452.1474629420035, "count": 18220, "self": 0.2505403109987583, "children": { "env_step": { "total": 451.8969226310047, "count": 18220, "self": 329.0581107830242, "children": { "SubprocessEnvManager._take_step": { "total": 122.59194593798986, "count": 18220, "self": 1.7200507879844054, "children": { "TorchPolicy.evaluate": { "total": 120.87189515000546, "count": 18220, "self": 120.87189515000546 } } }, "workers": { "total": 0.24686590999067448, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 455.44502556599434, "count": 18220, "is_parallel": true, "self": 215.74383837899347, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005989437000039288, "count": 1, "is_parallel": true, "self": 0.004152075999968474, "children": { "_process_rank_one_or_two_observation": { "total": 0.001837361000070814, "count": 10, "is_parallel": true, "self": 0.001837361000070814 } } }, "UnityEnvironment.step": { "total": 0.04247510400000465, "count": 1, "is_parallel": true, "self": 0.00038299799996366346, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003255010000202674, "count": 1, "is_parallel": true, "self": 0.0003255010000202674 }, "communicator.exchange": { "total": 0.03984051700001601, "count": 1, "is_parallel": true, "self": 0.03984051700001601 }, "steps_from_proto": { "total": 0.001926088000004711, "count": 1, "is_parallel": true, "self": 0.00040701399996123655, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015190740000434744, "count": 10, "is_parallel": true, "self": 0.0015190740000434744 } } } } } } }, "UnityEnvironment.step": { "total": 239.70118718700087, "count": 18219, "is_parallel": true, "self": 9.493560342005367, "children": { "UnityEnvironment._generate_step_input": { "total": 5.161319629998616, "count": 18219, "is_parallel": true, "self": 5.161319629998616 }, "communicator.exchange": { "total": 192.7017806459969, "count": 18219, "is_parallel": true, "self": 192.7017806459969 }, "steps_from_proto": { "total": 32.34452656899998, "count": 18219, "is_parallel": true, "self": 6.114858419981829, "children": { "_process_rank_one_or_two_observation": { "total": 26.229668149018153, "count": 182190, "is_parallel": true, "self": 26.229668149018153 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.757199995874544e-05, "count": 1, "self": 9.757199995874544e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.645890827999, "count": 421816, "is_parallel": true, "self": 9.481313105962386, "children": { "process_trajectory": { "total": 245.223524254037, "count": 421816, "is_parallel": true, "self": 244.09357478803713, "children": { "RLTrainer._checkpoint": { "total": 1.1299494659998572, "count": 4, "is_parallel": true, "self": 1.1299494659998572 } } }, "_update_policy": { "total": 193.9410534679996, "count": 90, "is_parallel": true, "self": 73.46791608699584, "children": { "TorchPPOOptimizer.update": { "total": 120.47313738100377, "count": 4587, "is_parallel": true, "self": 120.47313738100377 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21737427999994452, "count": 1, "self": 0.0011522449999574746, "children": { "RLTrainer._checkpoint": { "total": 0.21622203499998705, "count": 1, "self": 0.21622203499998705 } } } } } } }