{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8254134058952332, "min": 0.8192501068115234, "max": 2.8625054359436035, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7890.126953125, "min": 7890.126953125, "max": 29314.91796875, "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": 12.562621116638184, "min": 0.3788403272628784, "max": 12.562621116638184, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2449.711181640625, "min": 73.49502563476562, "max": 2548.38623046875, "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": 0.06510533461593748, "min": 0.06268487438850856, "max": 0.07305206112610618, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26042133846374993, "min": 0.25073949755403424, "max": 0.3544905325363609, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19600280067499948, "min": 0.12619268607151896, "max": 0.2817707290836409, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7840112026999979, "min": 0.5047707442860758, "max": 1.4088536454182046, "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": 24.954545454545453, "min": 3.522727272727273, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 155.0, "max": 1341.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.522727272727273, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 155.0, "max": 1341.0, "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": "1704971937", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704972418" }, "total": 480.3816874149999, "count": 1, "self": 0.4426097909998816, "children": { "run_training.setup": { "total": 0.0748676760000535, "count": 1, "self": 0.0748676760000535 }, "TrainerController.start_learning": { "total": 479.86420994799994, "count": 1, "self": 0.5876081040223653, "children": { "TrainerController._reset_env": { "total": 3.455411470000058, "count": 1, "self": 3.455411470000058 }, "TrainerController.advance": { "total": 475.73015454897745, "count": 18199, "self": 0.29548481099425317, "children": { "env_step": { "total": 475.4346697379832, "count": 18199, "self": 319.17544618197576, "children": { "SubprocessEnvManager._take_step": { "total": 155.96336760899874, "count": 18199, "self": 1.5579732409998996, "children": { "TorchPolicy.evaluate": { "total": 154.40539436799884, "count": 18199, "self": 154.40539436799884 } } }, "workers": { "total": 0.2958559470087039, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 478.4721633890133, "count": 18199, "is_parallel": true, "self": 235.00777291702173, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006783176999988427, "count": 1, "is_parallel": true, "self": 0.005450802999916959, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013323740000714679, "count": 10, "is_parallel": true, "self": 0.0013323740000714679 } } }, "UnityEnvironment.step": { "total": 0.04063502700000754, "count": 1, "is_parallel": true, "self": 0.0006618500000286076, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004095629999483208, "count": 1, "is_parallel": true, "self": 0.0004095629999483208 }, "communicator.exchange": { "total": 0.0371528790000184, "count": 1, "is_parallel": true, "self": 0.0371528790000184 }, "steps_from_proto": { "total": 0.0024107350000122096, "count": 1, "is_parallel": true, "self": 0.0006255179999925531, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017852170000196566, "count": 10, "is_parallel": true, "self": 0.0017852170000196566 } } } } } } }, "UnityEnvironment.step": { "total": 243.46439047199158, "count": 18198, "is_parallel": true, "self": 11.098562268988871, "children": { "UnityEnvironment._generate_step_input": { "total": 5.626211925989537, "count": 18198, "is_parallel": true, "self": 5.626211925989537 }, "communicator.exchange": { "total": 191.2789420430155, "count": 18198, "is_parallel": true, "self": 191.2789420430155 }, "steps_from_proto": { "total": 35.46067423399768, "count": 18198, "is_parallel": true, "self": 6.717906206001203, "children": { "_process_rank_one_or_two_observation": { "total": 28.742768027996476, "count": 181980, "is_parallel": true, "self": 28.742768027996476 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013854100006938097, "count": 1, "self": 0.00013854100006938097, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.1418045919619, "count": 677962, "is_parallel": true, "self": 14.365914527985979, "children": { "process_trajectory": { "total": 264.264056363975, "count": 677962, "is_parallel": true, "self": 263.5045220259751, "children": { "RLTrainer._checkpoint": { "total": 0.7595343379998667, "count": 4, "is_parallel": true, "self": 0.7595343379998667 } } }, "_update_policy": { "total": 191.51183370000092, "count": 90, "is_parallel": true, "self": 64.23059886300257, "children": { "TorchPPOOptimizer.update": { "total": 127.28123483699835, "count": 4587, "is_parallel": true, "self": 127.28123483699835 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0908972839999933, "count": 1, "self": 0.0009661040000992216, "children": { "RLTrainer._checkpoint": { "total": 0.08993117999989408, "count": 1, "self": 0.08993117999989408 } } } } } } }