{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0430805683135986, "min": 1.0430805683135986, "max": 2.870999574661255, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9982.28125, "min": 9982.28125, "max": 29559.8125, "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": 12.380651473999023, "min": 0.41055312752723694, "max": 12.45952320098877, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2414.22705078125, "min": 79.64730834960938, "max": 2531.13232421875, "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": 0.06655441671746837, "min": 0.05881946563963806, "max": 0.07534095324945692, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26621766686987347, "min": 0.2554512399057036, "max": 0.37670476624728455, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23552296960762903, "min": 0.12667855343954892, "max": 0.3327737209259295, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9420918784305161, "min": 0.5067142137581957, "max": 1.6638686046296476, "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": 24.65909090909091, "min": 3.340909090909091, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1085.0, "min": 147.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.65909090909091, "min": 3.340909090909091, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1085.0, "min": 147.0, "max": 1360.0, "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": "1700122939", "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": "1700123402" }, "total": 463.152802091, "count": 1, "self": 0.7294393010000704, "children": { "run_training.setup": { "total": 0.04992136999999275, "count": 1, "self": 0.04992136999999275 }, "TrainerController.start_learning": { "total": 462.37344141999995, "count": 1, "self": 0.5325061319978772, "children": { "TrainerController._reset_env": { "total": 9.011505309999961, "count": 1, "self": 9.011505309999961 }, "TrainerController.advance": { "total": 452.66486456300214, "count": 18206, "self": 0.24500317900367463, "children": { "env_step": { "total": 452.41986138399847, "count": 18206, "self": 311.28007971699816, "children": { "SubprocessEnvManager._take_step": { "total": 140.87599382699972, "count": 18206, "self": 1.40463041099855, "children": { "TorchPolicy.evaluate": { "total": 139.47136341600117, "count": 18206, "self": 139.47136341600117 } } }, "workers": { "total": 0.26378784000058886, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 461.03409829899095, "count": 18206, "is_parallel": true, "self": 225.85996375799124, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005943199000000732, "count": 1, "is_parallel": true, "self": 0.004471827999964262, "children": { "_process_rank_one_or_two_observation": { "total": 0.00147137100003647, "count": 10, "is_parallel": true, "self": 0.00147137100003647 } } }, "UnityEnvironment.step": { "total": 0.0346979690000353, "count": 1, "is_parallel": true, "self": 0.0006267290000323555, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005489540000098714, "count": 1, "is_parallel": true, "self": 0.0005489540000098714 }, "communicator.exchange": { "total": 0.03169036799999958, "count": 1, "is_parallel": true, "self": 0.03169036799999958 }, "steps_from_proto": { "total": 0.0018319179999934931, "count": 1, "is_parallel": true, "self": 0.00035018399995578875, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014817340000377044, "count": 10, "is_parallel": true, "self": 0.0014817340000377044 } } } } } } }, "UnityEnvironment.step": { "total": 235.17413454099972, "count": 18205, "is_parallel": true, "self": 10.43471590500991, "children": { "UnityEnvironment._generate_step_input": { "total": 5.331044070992789, "count": 18205, "is_parallel": true, "self": 5.331044070992789 }, "communicator.exchange": { "total": 186.61918964600352, "count": 18205, "is_parallel": true, "self": 186.61918964600352 }, "steps_from_proto": { "total": 32.7891849189935, "count": 18205, "is_parallel": true, "self": 6.116570912986276, "children": { "_process_rank_one_or_two_observation": { "total": 26.672614006007223, "count": 182050, "is_parallel": true, "self": 26.672614006007223 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016424099999312602, "count": 1, "self": 0.00016424099999312602, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.9533564960385, "count": 475443, "is_parallel": true, "self": 9.69019578204228, "children": { "process_trajectory": { "total": 253.0326083349958, "count": 475443, "is_parallel": true, "self": 252.02077165999572, "children": { "RLTrainer._checkpoint": { "total": 1.0118366750000973, "count": 4, "is_parallel": true, "self": 1.0118366750000973 } } }, "_update_policy": { "total": 186.23055237900041, "count": 90, "is_parallel": true, "self": 61.50642759900086, "children": { "TorchPPOOptimizer.update": { "total": 124.72412477999956, "count": 4584, "is_parallel": true, "self": 124.72412477999956 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1644011739999769, "count": 1, "self": 0.0011989229999471718, "children": { "RLTrainer._checkpoint": { "total": 0.16320225100002972, "count": 1, "self": 0.16320225100002972 } } } } } } }