{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8873598575592041, "min": 0.8873598575592041, "max": 2.857192039489746, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8472.51171875, "min": 8472.51171875, "max": 29260.50390625, "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": 12.900227546691895, "min": 0.3158401548862457, "max": 12.900227546691895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.54443359375, "min": 61.27299118041992, "max": 2592.0751953125, "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": 0.0668118380374782, "min": 0.0651139115990886, "max": 0.07173888658579408, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2672473521499128, "min": 0.2604556463963544, "max": 0.35467591713520463, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17821636704691485, "min": 0.11747463420375852, "max": 0.28628270339732076, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7128654681876594, "min": 0.4698985368150341, "max": 1.4314135169866038, "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": 25.454545454545453, "min": 3.409090909090909, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 150.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.409090909090909, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 150.0, "max": 1392.0, "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": "1677167571", "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": "1.22.4", "end_time_seconds": "1677168185" }, "total": 614.07469524, "count": 1, "self": 0.5927766849999898, "children": { "run_training.setup": { "total": 0.1476218600000152, "count": 1, "self": 0.1476218600000152 }, "TrainerController.start_learning": { "total": 613.3342966949999, "count": 1, "self": 0.8809309849995088, "children": { "TrainerController._reset_env": { "total": 6.9334763790000125, "count": 1, "self": 6.9334763790000125 }, "TrainerController.advance": { "total": 605.3699830320003, "count": 18201, "self": 0.42970611800114966, "children": { "env_step": { "total": 604.9402769139991, "count": 18201, "self": 475.44441866798604, "children": { "SubprocessEnvManager._take_step": { "total": 129.06946824300945, "count": 18201, "self": 2.625341695010718, "children": { "TorchPolicy.evaluate": { "total": 126.44412654799874, "count": 18201, "self": 21.03455597799143, "children": { "TorchPolicy.sample_actions": { "total": 105.4095705700073, "count": 18201, "self": 105.4095705700073 } } } } }, "workers": { "total": 0.4263900030036325, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 610.9053553090034, "count": 18201, "is_parallel": true, "self": 272.9443326890107, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004917073999990862, "count": 1, "is_parallel": true, "self": 0.0034180729999775394, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014990010000133225, "count": 10, "is_parallel": true, "self": 0.0014990010000133225 } } }, "UnityEnvironment.step": { "total": 0.05105843000001187, "count": 1, "is_parallel": true, "self": 0.0007266360000244276, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044021399997973276, "count": 1, "is_parallel": true, "self": 0.00044021399997973276 }, "communicator.exchange": { "total": 0.04753440500002171, "count": 1, "is_parallel": true, "self": 0.04753440500002171 }, "steps_from_proto": { "total": 0.0023571749999860003, "count": 1, "is_parallel": true, "self": 0.0005163760000073125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018407989999786878, "count": 10, "is_parallel": true, "self": 0.0018407989999786878 } } } } } } }, "UnityEnvironment.step": { "total": 337.9610226199927, "count": 18200, "is_parallel": true, "self": 14.023425474980286, "children": { "UnityEnvironment._generate_step_input": { "total": 7.64241397400292, "count": 18200, "is_parallel": true, "self": 7.64241397400292 }, "communicator.exchange": { "total": 271.30734948500594, "count": 18200, "is_parallel": true, "self": 271.30734948500594 }, "steps_from_proto": { "total": 44.98783368600357, "count": 18200, "is_parallel": true, "self": 10.447215401011931, "children": { "_process_rank_one_or_two_observation": { "total": 34.54061828499164, "count": 182000, "is_parallel": true, "self": 34.54061828499164 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001838880000377685, "count": 1, "self": 0.0001838880000377685, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 600.0377256159707, "count": 600020, "is_parallel": true, "self": 15.893219618960757, "children": { "process_trajectory": { "total": 330.3091263330091, "count": 600020, "is_parallel": true, "self": 329.465156544009, "children": { "RLTrainer._checkpoint": { "total": 0.8439697890000843, "count": 4, "is_parallel": true, "self": 0.8439697890000843 } } }, "_update_policy": { "total": 253.83537966400075, "count": 90, "is_parallel": true, "self": 80.97694738499678, "children": { "TorchPPOOptimizer.update": { "total": 172.85843227900398, "count": 4587, "is_parallel": true, "self": 172.85843227900398 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14972241100008432, "count": 1, "self": 0.001316302000077485, "children": { "RLTrainer._checkpoint": { "total": 0.14840610900000684, "count": 1, "self": 0.14840610900000684 } } } } } } }