{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9619103074073792, "min": 0.9619103074073792, "max": 2.8682756423950195, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9216.0625, "min": 9216.0625, "max": 29374.01171875, "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": 11.916253089904785, "min": 0.26223844289779663, "max": 11.943327903747559, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2323.66943359375, "min": 50.87425994873047, "max": 2436.43896484375, "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": 0.07064844631160809, "min": 0.06045420648426765, "max": 0.07321314640598846, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28259378524643236, "min": 0.2564524323291456, "max": 0.3660657320299423, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1791175969456341, "min": 0.11523861722454574, "max": 0.27982308069864914, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7164703877825364, "min": 0.460954468898183, "max": 1.3991154034932456, "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": 22.818181818181817, "min": 3.409090909090909, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1004.0, "min": 150.0, "max": 1290.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.818181818181817, "min": 3.409090909090909, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1004.0, "min": 150.0, "max": 1290.0, "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": "1703604744", "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=SnowballTarget2 --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": "1703605186" }, "total": 442.4196425240002, "count": 1, "self": 0.5831587689999651, "children": { "run_training.setup": { "total": 0.07132370299996182, "count": 1, "self": 0.07132370299996182 }, "TrainerController.start_learning": { "total": 441.7651600520003, "count": 1, "self": 0.5767614159717596, "children": { "TrainerController._reset_env": { "total": 2.5750052870002946, "count": 1, "self": 2.5750052870002946 }, "TrainerController.advance": { "total": 438.47794382902794, "count": 18216, "self": 0.2715893050194609, "children": { "env_step": { "total": 438.2063545240085, "count": 18216, "self": 289.2228420800707, "children": { "SubprocessEnvManager._take_step": { "total": 148.69773202094711, "count": 18216, "self": 1.4530100589499853, "children": { "TorchPolicy.evaluate": { "total": 147.24472196199713, "count": 18216, "self": 147.24472196199713 } } }, "workers": { "total": 0.2857804229906833, "count": 18216, "self": 0.0, "children": { "worker_root": { "total": 440.4255836120101, "count": 18216, "is_parallel": true, "self": 215.97380556803319, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002683485000034125, "count": 1, "is_parallel": true, "self": 0.0006360020011015877, "children": { "_process_rank_one_or_two_observation": { "total": 0.002047482998932537, "count": 10, "is_parallel": true, "self": 0.002047482998932537 } } }, "UnityEnvironment.step": { "total": 0.036522253999919485, "count": 1, "is_parallel": true, "self": 0.0006443729994316527, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004497050003919867, "count": 1, "is_parallel": true, "self": 0.0004497050003919867 }, "communicator.exchange": { "total": 0.033549489000051835, "count": 1, "is_parallel": true, "self": 0.033549489000051835 }, "steps_from_proto": { "total": 0.0018786870000440103, "count": 1, "is_parallel": true, "self": 0.0003846819995487749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014940050004952354, "count": 10, "is_parallel": true, "self": 0.0014940050004952354 } } } } } } }, "UnityEnvironment.step": { "total": 224.4517780439769, "count": 18215, "is_parallel": true, "self": 10.452371109970954, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2891745199963225, "count": 18215, "is_parallel": true, "self": 5.2891745199963225 }, "communicator.exchange": { "total": 175.69493266398422, "count": 18215, "is_parallel": true, "self": 175.69493266398422 }, "steps_from_proto": { "total": 33.015299750025406, "count": 18215, "is_parallel": true, "self": 6.147425217900491, "children": { "_process_rank_one_or_two_observation": { "total": 26.867874532124915, "count": 182150, "is_parallel": true, "self": 26.867874532124915 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001335990000370657, "count": 1, "self": 0.0001335990000370657, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 433.12787389409505, "count": 661099, "is_parallel": true, "self": 13.968666580098215, "children": { "process_trajectory": { "total": 239.13842157599856, "count": 661099, "is_parallel": true, "self": 238.34902952899847, "children": { "RLTrainer._checkpoint": { "total": 0.7893920470000921, "count": 4, "is_parallel": true, "self": 0.7893920470000921 } } }, "_update_policy": { "total": 180.02078573799827, "count": 90, "is_parallel": true, "self": 56.372759893011334, "children": { "TorchPPOOptimizer.update": { "total": 123.64802584498693, "count": 4587, "is_parallel": true, "self": 123.64802584498693 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1353159210002559, "count": 1, "self": 0.0012274980003894598, "children": { "RLTrainer._checkpoint": { "total": 0.13408842299986645, "count": 1, "self": 0.13408842299986645 } } } } } } }