{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9555334448814392, "min": 0.9555334448814392, "max": 2.8548974990844727, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9123.43359375, "min": 9123.43359375, "max": 29299.8125, "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": 12.473793029785156, "min": 0.4171019494533539, "max": 12.473793029785156, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2432.3896484375, "min": 80.91777801513672, "max": 2531.17626953125, "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": 0.06567343947244808, "min": 0.05987373982469424, "max": 0.07342051074060603, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2626937578897923, "min": 0.23949495929877695, "max": 0.36710255370303013, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24426561886189033, "min": 0.10427121941899589, "max": 0.2959735061608109, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9770624754475613, "min": 0.41708487767598357, "max": 1.4798675308040545, "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": 24.34090909090909, "min": 3.159090909090909, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1071.0, "min": 139.0, "max": 1356.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.34090909090909, "min": 3.159090909090909, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1071.0, "min": 139.0, "max": 1356.0, "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": "1718821954", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718822581" }, "total": 626.8165642009999, "count": 1, "self": 0.9601652729998023, "children": { "run_training.setup": { "total": 0.0731114330001219, "count": 1, "self": 0.0731114330001219 }, "TrainerController.start_learning": { "total": 625.783287495, "count": 1, "self": 0.9477788009344295, "children": { "TrainerController._reset_env": { "total": 4.631532656000672, "count": 1, "self": 4.631532656000672 }, "TrainerController.advance": { "total": 620.041157538064, "count": 18209, "self": 0.4479399120746166, "children": { "env_step": { "total": 619.5932176259894, "count": 18209, "self": 473.17192338402765, "children": { "SubprocessEnvManager._take_step": { "total": 145.99062274600055, "count": 18209, "self": 2.7934113630108186, "children": { "TorchPolicy.evaluate": { "total": 143.19721138298974, "count": 18209, "self": 143.19721138298974 } } }, "workers": { "total": 0.43067149596117815, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 623.60458500802, "count": 18209, "is_parallel": true, "self": 301.00780207795015, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008480574000714114, "count": 1, "is_parallel": true, "self": 0.006211496999640076, "children": { "_process_rank_one_or_two_observation": { "total": 0.002269077001074038, "count": 10, "is_parallel": true, "self": 0.002269077001074038 } } }, "UnityEnvironment.step": { "total": 0.046306006999657257, "count": 1, "is_parallel": true, "self": 0.0010470369998074602, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045505900015996303, "count": 1, "is_parallel": true, "self": 0.00045505900015996303 }, "communicator.exchange": { "total": 0.0421020639996641, "count": 1, "is_parallel": true, "self": 0.0421020639996641 }, "steps_from_proto": { "total": 0.0027018470000257366, "count": 1, "is_parallel": true, "self": 0.00048090299969771877, "children": { "_process_rank_one_or_two_observation": { "total": 0.002220944000328018, "count": 10, "is_parallel": true, "self": 0.002220944000328018 } } } } } } }, "UnityEnvironment.step": { "total": 322.5967829300698, "count": 18208, "is_parallel": true, "self": 15.625988228004644, "children": { "UnityEnvironment._generate_step_input": { "total": 7.954462719008916, "count": 18208, "is_parallel": true, "self": 7.954462719008916 }, "communicator.exchange": { "total": 253.3719724150369, "count": 18208, "is_parallel": true, "self": 253.3719724150369 }, "steps_from_proto": { "total": 45.644359568019354, "count": 18208, "is_parallel": true, "self": 8.983200387882789, "children": { "_process_rank_one_or_two_observation": { "total": 36.661159180136565, "count": 182080, "is_parallel": true, "self": 36.661159180136565 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00024196300000767224, "count": 1, "self": 0.00024196300000767224, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 612.6195133881847, "count": 800862, "is_parallel": true, "self": 19.36623046823297, "children": { "process_trajectory": { "total": 326.8901134399475, "count": 800862, "is_parallel": true, "self": 324.91897176194834, "children": { "RLTrainer._checkpoint": { "total": 1.971141677999185, "count": 4, "is_parallel": true, "self": 1.971141677999185 } } }, "_update_policy": { "total": 266.3631694800042, "count": 90, "is_parallel": true, "self": 75.38432513700081, "children": { "TorchPPOOptimizer.update": { "total": 190.9788443430034, "count": 4587, "is_parallel": true, "self": 190.9788443430034 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1625765370008594, "count": 1, "self": 0.0017918970006576274, "children": { "RLTrainer._checkpoint": { "total": 0.16078464000020176, "count": 1, "self": 0.16078464000020176 } } } } } } }