{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9145931005477905, "min": 0.9145931005477905, "max": 2.861435890197754, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8752.65625, "min": 8752.65625, "max": 29303.96484375, "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": 12.90573787689209, "min": 0.32144421339035034, "max": 12.90573787689209, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.618896484375, "min": 62.36017608642578, "max": 2621.76611328125, "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": 0.06318793616510981, "min": 0.06094911168346538, "max": 0.07266912313107418, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25275174466043926, "min": 0.24379644673386153, "max": 0.36302302162763295, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1963240519604262, "min": 0.12218840024776428, "max": 0.2905629719589271, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7852962078417048, "min": 0.48875360099105714, "max": 1.4528148597946355, "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": 25.15909090909091, "min": 3.1818181818181817, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 140.0, "max": 1410.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.1818181818181817, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 140.0, "max": 1410.0, "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": "1709326616", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709327092" }, "total": 475.8564017489998, "count": 1, "self": 0.4351700890001666, "children": { "run_training.setup": { "total": 0.05432287499979793, "count": 1, "self": 0.05432287499979793 }, "TrainerController.start_learning": { "total": 475.36690878499985, "count": 1, "self": 0.6168506350004463, "children": { "TrainerController._reset_env": { "total": 3.0637042080002175, "count": 1, "self": 3.0637042080002175 }, "TrainerController.advance": { "total": 471.589776290999, "count": 18201, "self": 0.29858697998088246, "children": { "env_step": { "total": 471.2911893110181, "count": 18201, "self": 307.9078586560686, "children": { "SubprocessEnvManager._take_step": { "total": 163.07124795698564, "count": 18201, "self": 1.5864059299233304, "children": { "TorchPolicy.evaluate": { "total": 161.4848420270623, "count": 18201, "self": 161.4848420270623 } } }, "workers": { "total": 0.31208269796388777, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 474.1838290669948, "count": 18201, "is_parallel": true, "self": 234.4529371249464, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005565258999922662, "count": 1, "is_parallel": true, "self": 0.003891117999501148, "children": { "_process_rank_one_or_two_observation": { "total": 0.001674141000421514, "count": 10, "is_parallel": true, "self": 0.001674141000421514 } } }, "UnityEnvironment.step": { "total": 0.03852432699977726, "count": 1, "is_parallel": true, "self": 0.0007312980001188407, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004896969999208522, "count": 1, "is_parallel": true, "self": 0.0004896969999208522 }, "communicator.exchange": { "total": 0.03516706299978978, "count": 1, "is_parallel": true, "self": 0.03516706299978978 }, "steps_from_proto": { "total": 0.002136268999947788, "count": 1, "is_parallel": true, "self": 0.0004102999987480871, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017259690011997009, "count": 10, "is_parallel": true, "self": 0.0017259690011997009 } } } } } } }, "UnityEnvironment.step": { "total": 239.7308919420484, "count": 18200, "is_parallel": true, "self": 11.181636911076112, "children": { "UnityEnvironment._generate_step_input": { "total": 5.777636019952752, "count": 18200, "is_parallel": true, "self": 5.777636019952752 }, "communicator.exchange": { "total": 186.58514664000086, "count": 18200, "is_parallel": true, "self": 186.58514664000086 }, "steps_from_proto": { "total": 36.18647237101868, "count": 18200, "is_parallel": true, "self": 6.82730938105351, "children": { "_process_rank_one_or_two_observation": { "total": 29.35916298996517, "count": 182000, "is_parallel": true, "self": 29.35916298996517 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016538199997739866, "count": 1, "self": 0.00016538199997739866, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.79683770814336, "count": 662324, "is_parallel": true, "self": 14.90269188502225, "children": { "process_trajectory": { "total": 259.2961455261179, "count": 662324, "is_parallel": true, "self": 258.5509514991177, "children": { "RLTrainer._checkpoint": { "total": 0.7451940270002524, "count": 4, "is_parallel": true, "self": 0.7451940270002524 } } }, "_update_policy": { "total": 191.59800029700318, "count": 90, "is_parallel": true, "self": 53.322837587019876, "children": { "TorchPPOOptimizer.update": { "total": 138.2751627099833, "count": 4587, "is_parallel": true, "self": 138.2751627099833 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09641226900021138, "count": 1, "self": 0.0009951209999599087, "children": { "RLTrainer._checkpoint": { "total": 0.09541714800025147, "count": 1, "self": 0.09541714800025147 } } } } } } }