{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9290400743484497, "min": 0.9290400743484497, "max": 2.8718738555908203, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8870.474609375, "min": 8870.474609375, "max": 29379.26953125, "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": 13.124446868896484, "min": 0.39283815026283264, "max": 13.124446868896484, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2559.26708984375, "min": 76.21060180664062, "max": 2656.20703125, "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": 0.06771134205023283, "min": 0.06136412849722832, "max": 0.07627490205774723, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2708453682009313, "min": 0.24607546463398738, "max": 0.38137451028873615, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1984056109452949, "min": 0.11946889817230769, "max": 0.28876863354269194, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7936224437811796, "min": 0.47787559268923074, "max": 1.4235675311556049, "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": 25.795454545454547, "min": 3.5681818181818183, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1135.0, "min": 157.0, "max": 1424.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.795454545454547, "min": 3.5681818181818183, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1135.0, "min": 157.0, "max": 1424.0, "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": "1695763085", "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": "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": "1695763590" }, "total": 505.04567885899996, "count": 1, "self": 0.4851849819998506, "children": { "run_training.setup": { "total": 0.0645541140000887, "count": 1, "self": 0.0645541140000887 }, "TrainerController.start_learning": { "total": 504.495939763, "count": 1, "self": 0.6297622929997715, "children": { "TrainerController._reset_env": { "total": 5.493438429999969, "count": 1, "self": 5.493438429999969 }, "TrainerController.advance": { "total": 498.230102354, "count": 18201, "self": 0.3465102619884419, "children": { "env_step": { "total": 497.88359209201155, "count": 18201, "self": 363.86895243001686, "children": { "SubprocessEnvManager._take_step": { "total": 133.68314318999455, "count": 18201, "self": 1.9648216749957328, "children": { "TorchPolicy.evaluate": { "total": 131.71832151499882, "count": 18201, "self": 131.71832151499882 } } }, "workers": { "total": 0.3314964720001399, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 502.79582365901683, "count": 18201, "is_parallel": true, "self": 234.25502867302737, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006263484999976754, "count": 1, "is_parallel": true, "self": 0.003817759000071419, "children": { "_process_rank_one_or_two_observation": { "total": 0.002445725999905335, "count": 10, "is_parallel": true, "self": 0.002445725999905335 } } }, "UnityEnvironment.step": { "total": 0.037822075000008226, "count": 1, "is_parallel": true, "self": 0.0006573379998826567, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004677080000874412, "count": 1, "is_parallel": true, "self": 0.0004677080000874412 }, "communicator.exchange": { "total": 0.03354297700002462, "count": 1, "is_parallel": true, "self": 0.03354297700002462 }, "steps_from_proto": { "total": 0.0031540520000135075, "count": 1, "is_parallel": true, "self": 0.0013561749998416417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017978770001718658, "count": 10, "is_parallel": true, "self": 0.0017978770001718658 } } } } } } }, "UnityEnvironment.step": { "total": 268.54079498598946, "count": 18200, "is_parallel": true, "self": 10.945800701982648, "children": { "UnityEnvironment._generate_step_input": { "total": 5.654592889002174, "count": 18200, "is_parallel": true, "self": 5.654592889002174 }, "communicator.exchange": { "total": 214.0341633369959, "count": 18200, "is_parallel": true, "self": 214.0341633369959 }, "steps_from_proto": { "total": 37.90623805800874, "count": 18200, "is_parallel": true, "self": 7.214507931994035, "children": { "_process_rank_one_or_two_observation": { "total": 30.691730126014704, "count": 182000, "is_parallel": true, "self": 30.691730126014704 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011168000014549762, "count": 1, "self": 0.00011168000014549762, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 494.56817940102565, "count": 466845, "is_parallel": true, "self": 10.296956894064238, "children": { "process_trajectory": { "total": 271.06338269696175, "count": 466845, "is_parallel": true, "self": 269.6853422549616, "children": { "RLTrainer._checkpoint": { "total": 1.378040442000156, "count": 4, "is_parallel": true, "self": 1.378040442000156 } } }, "_update_policy": { "total": 213.20783980999965, "count": 90, "is_parallel": true, "self": 83.79046164000283, "children": { "TorchPPOOptimizer.update": { "total": 129.41737816999682, "count": 4587, "is_parallel": true, "self": 129.41737816999682 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14252500600014173, "count": 1, "self": 0.0008896320000530977, "children": { "RLTrainer._checkpoint": { "total": 0.14163537400008863, "count": 1, "self": 0.14163537400008863 } } } } } } }