{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6556198000907898, "min": 0.6556198000907898, "max": 2.8616464138031006, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6238.22265625, "min": 6238.22265625, "max": 29306.12109375, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.972919464111328, "min": 0.29344210028648376, "max": 14.223943710327148, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2724.71923828125, "min": 56.927764892578125, "max": 2915.908447265625, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06891079435830333, "min": 0.06007124235172038, "max": 0.07707131814494657, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2756431774332133, "min": 0.24028496940688152, "max": 0.38535659072473283, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14685648712603483, "min": 0.11214490902299683, "max": 0.28962309563568994, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5874259485041393, "min": 0.4485796360919873, "max": 1.327513700898956, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.3764995412000027e-06, "min": 1.3764995412000027e-06, "max": 0.0002983764005411999, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.505998164800011e-06, "min": 5.505998164800011e-06, "max": 0.001477032007656, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10045880000000001, "min": 0.10045880000000001, "max": 0.1994588, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40183520000000006, "min": 0.40183520000000006, "max": 0.992344, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.289412000000004e-05, "min": 3.289412000000004e-05, "max": 0.00497299412, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00013157648000000017, "min": 0.00013157648000000017, "max": 0.0246179656, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.444444444444443, "min": 3.0454545454545454, "max": 28.227272727272727, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1235.0, "min": 134.0, "max": 1538.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.444444444444443, "min": 3.0454545454545454, "max": 28.227272727272727, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1235.0, "min": 134.0, "max": 1538.0, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704282374", "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": "1704284666" }, "total": 2292.328304225, "count": 1, "self": 0.44431485899986, "children": { "run_training.setup": { "total": 0.05248547400003645, "count": 1, "self": 0.05248547400003645 }, "TrainerController.start_learning": { "total": 2291.831503892, "count": 1, "self": 2.8727537150116405, "children": { "TrainerController._reset_env": { "total": 3.2193444739999677, "count": 1, "self": 3.2193444739999677 }, "TrainerController.advance": { "total": 2285.644657805988, "count": 90935, "self": 1.489981793959032, "children": { "env_step": { "total": 2284.154676012029, "count": 90935, "self": 1498.9616912490487, "children": { "SubprocessEnvManager._take_step": { "total": 783.7169014840048, "count": 90935, "self": 7.491208335028773, "children": { "TorchPolicy.evaluate": { "total": 776.225693148976, "count": 90935, "self": 776.225693148976 } } }, "workers": { "total": 1.4760832789756932, "count": 90935, "self": 0.0, "children": { "worker_root": { "total": 2285.3747079809837, "count": 90935, "is_parallel": true, "self": 1122.6868134669612, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052974980000044525, "count": 1, "is_parallel": true, "self": 0.004004996999924515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012925010000799375, "count": 10, "is_parallel": true, "self": 0.0012925010000799375 } } }, "UnityEnvironment.step": { "total": 0.03913824200003546, "count": 1, "is_parallel": true, "self": 0.000681891999988693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042681000002176006, "count": 1, "is_parallel": true, "self": 0.00042681000002176006 }, "communicator.exchange": { "total": 0.03592935500000749, "count": 1, "is_parallel": true, "self": 0.03592935500000749 }, "steps_from_proto": { "total": 0.002100185000017518, "count": 1, "is_parallel": true, "self": 0.0004115399999591318, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016886450000583864, "count": 10, "is_parallel": true, "self": 0.0016886450000583864 } } } } } } }, "UnityEnvironment.step": { "total": 1162.6878945140224, "count": 90934, "is_parallel": true, "self": 54.87933442413441, "children": { "UnityEnvironment._generate_step_input": { "total": 27.785904660984556, "count": 90934, "is_parallel": true, "self": 27.785904660984556 }, "communicator.exchange": { "total": 903.4905963699863, "count": 90934, "is_parallel": true, "self": 903.4905963699863 }, "steps_from_proto": { "total": 176.53205905891718, "count": 90934, "is_parallel": true, "self": 33.06144935106772, "children": { "_process_rank_one_or_two_observation": { "total": 143.47060970784946, "count": 909340, "is_parallel": true, "self": 143.47060970784946 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022406200014302158, "count": 1, "self": 0.00022406200014302158, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2256.9824222361353, "count": 3470729, "is_parallel": true, "self": 73.82584219507453, "children": { "process_trajectory": { "total": 1243.1144788980619, "count": 3470729, "is_parallel": true, "self": 1240.0073659410616, "children": { "RLTrainer._checkpoint": { "total": 3.107112957000254, "count": 20, "is_parallel": true, "self": 3.107112957000254 } } }, "_update_policy": { "total": 940.0421011429992, "count": 454, "is_parallel": true, "self": 294.46607319399584, "children": { "TorchPPOOptimizer.update": { "total": 645.5760279490033, "count": 23145, "is_parallel": true, "self": 645.5760279490033 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09452383500001815, "count": 1, "self": 0.001024473000143189, "children": { "RLTrainer._checkpoint": { "total": 0.09349936199987496, "count": 1, "self": 0.09349936199987496 } } } } } } }