{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.977387547492981, "min": 0.977387547492981, "max": 2.862623691558838, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9342.84765625, "min": 9342.84765625, "max": 29536.55078125, "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": 13.022972106933594, "min": 0.2525531053543091, "max": 13.022972106933594, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2539.4794921875, "min": 48.99530029296875, "max": 2617.3505859375, "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": 0.07502718082761539, "min": 0.062378122091888824, "max": 0.07511701486880923, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30010872331046157, "min": 0.2495124883675553, "max": 0.36488177264383176, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20352951320363025, "min": 0.10783614959070167, "max": 0.27790702156284275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.814118052814521, "min": 0.4313445983628067, "max": 1.3462764015969106, "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": 25.863636363636363, "min": 3.159090909090909, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1138.0, "min": 139.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.863636363636363, "min": 3.159090909090909, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1138.0, "min": 139.0, "max": 1396.0, "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": "1676974874", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676975359" }, "total": 484.9291071550001, "count": 1, "self": 0.4567324770000596, "children": { "run_training.setup": { "total": 0.11176468300004672, "count": 1, "self": 0.11176468300004672 }, "TrainerController.start_learning": { "total": 484.360609995, "count": 1, "self": 0.6879850979964885, "children": { "TrainerController._reset_env": { "total": 10.502832018999925, "count": 1, "self": 10.502832018999925 }, "TrainerController.advance": { "total": 472.9711188540034, "count": 18215, "self": 0.3179543109893075, "children": { "env_step": { "total": 472.6531645430141, "count": 18215, "self": 326.6843303409996, "children": { "SubprocessEnvManager._take_step": { "total": 145.65594777701654, "count": 18215, "self": 1.5701217800308314, "children": { "TorchPolicy.evaluate": { "total": 144.0858259969857, "count": 18215, "self": 31.87182019098077, "children": { "TorchPolicy.sample_actions": { "total": 112.21400580600493, "count": 18215, "self": 112.21400580600493 } } } } }, "workers": { "total": 0.3128864249979415, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 482.2852140980076, "count": 18215, "is_parallel": true, "self": 230.6962409660025, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009848980000015217, "count": 1, "is_parallel": true, "self": 0.0035116369999741437, "children": { "_process_rank_one_or_two_observation": { "total": 0.0063373430000410735, "count": 10, "is_parallel": true, "self": 0.0063373430000410735 } } }, "UnityEnvironment.step": { "total": 0.03508320299988554, "count": 1, "is_parallel": true, "self": 0.0005678519996763498, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004267510000772745, "count": 1, "is_parallel": true, "self": 0.0004267510000772745 }, "communicator.exchange": { "total": 0.03225652500009346, "count": 1, "is_parallel": true, "self": 0.03225652500009346 }, "steps_from_proto": { "total": 0.0018320750000384578, "count": 1, "is_parallel": true, "self": 0.0004339890003848268, "children": { "_process_rank_one_or_two_observation": { "total": 0.001398085999653631, "count": 10, "is_parallel": true, "self": 0.001398085999653631 } } } } } } }, "UnityEnvironment.step": { "total": 251.5889731320051, "count": 18214, "is_parallel": true, "self": 9.945516245005365, "children": { "UnityEnvironment._generate_step_input": { "total": 5.336493419985345, "count": 18214, "is_parallel": true, "self": 5.336493419985345 }, "communicator.exchange": { "total": 203.51991983800076, "count": 18214, "is_parallel": true, "self": 203.51991983800076 }, "steps_from_proto": { "total": 32.787043629013624, "count": 18214, "is_parallel": true, "self": 7.535119400937447, "children": { "_process_rank_one_or_two_observation": { "total": 25.251924228076177, "count": 182140, "is_parallel": true, "self": 25.251924228076177 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001441760000489012, "count": 1, "self": 0.0001441760000489012, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.5829029329825, "count": 430066, "is_parallel": true, "self": 10.53227170904529, "children": { "process_trajectory": { "total": 268.03537019093733, "count": 430066, "is_parallel": true, "self": 266.96975070093754, "children": { "RLTrainer._checkpoint": { "total": 1.06561948999979, "count": 4, "is_parallel": true, "self": 1.06561948999979 } } }, "_update_policy": { "total": 191.0152610329999, "count": 90, "is_parallel": true, "self": 66.32392700701303, "children": { "TorchPPOOptimizer.update": { "total": 124.69133402598686, "count": 4587, "is_parallel": true, "self": 124.69133402598686 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19852984800013473, "count": 1, "self": 0.0009927080002398725, "children": { "RLTrainer._checkpoint": { "total": 0.19753713999989486, "count": 1, "self": 0.19753713999989486 } } } } } } }