{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8234853148460388, "min": 0.8234853148460388, "max": 2.858184814453125, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7871.6962890625, "min": 7871.6962890625, "max": 29270.669921875, "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": 12.899338722229004, "min": 0.3852045238018036, "max": 12.899338722229004, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.37109375, "min": 74.72967529296875, "max": 2597.261474609375, "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": 0.06904152963041127, "min": 0.06300984059697858, "max": 0.07390666957103706, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2761661185216451, "min": 0.25340689864698984, "max": 0.3653889242011835, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18489532179984391, "min": 0.14039169973579657, "max": 0.28285256977759154, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7395812871993757, "min": 0.5615667989431863, "max": 1.376287923431864, "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": 25.25, "min": 3.8636363636363638, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 170.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.8636363636363638, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 170.0, "max": 1408.0, "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": "1699338252", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699338716" }, "total": 463.50703401799996, "count": 1, "self": 0.7429225619999329, "children": { "run_training.setup": { "total": 0.04482471500000429, "count": 1, "self": 0.04482471500000429 }, "TrainerController.start_learning": { "total": 462.719286741, "count": 1, "self": 0.582795504002263, "children": { "TrainerController._reset_env": { "total": 7.242100518000029, "count": 1, "self": 7.242100518000029 }, "TrainerController.advance": { "total": 454.8115471839977, "count": 18200, "self": 0.28190958100168473, "children": { "env_step": { "total": 454.529637602996, "count": 18200, "self": 311.7080695210007, "children": { "SubprocessEnvManager._take_step": { "total": 142.52627480399286, "count": 18200, "self": 1.4273617989897502, "children": { "TorchPolicy.evaluate": { "total": 141.0989130050031, "count": 18200, "self": 141.0989130050031 } } }, "workers": { "total": 0.29529327800241845, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 461.3832311170004, "count": 18200, "is_parallel": true, "self": 224.26634987599783, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0042946149999920635, "count": 1, "is_parallel": true, "self": 0.002984380999919267, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013102340000727963, "count": 10, "is_parallel": true, "self": 0.0013102340000727963 } } }, "UnityEnvironment.step": { "total": 0.06466057300002603, "count": 1, "is_parallel": true, "self": 0.0006198270000368211, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036466500000642554, "count": 1, "is_parallel": true, "self": 0.00036466500000642554 }, "communicator.exchange": { "total": 0.06180936200001952, "count": 1, "is_parallel": true, "self": 0.06180936200001952 }, "steps_from_proto": { "total": 0.0018667189999632683, "count": 1, "is_parallel": true, "self": 0.0003852589999837619, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014814599999795064, "count": 10, "is_parallel": true, "self": 0.0014814599999795064 } } } } } } }, "UnityEnvironment.step": { "total": 237.11688124100255, "count": 18199, "is_parallel": true, "self": 10.363532844010592, "children": { "UnityEnvironment._generate_step_input": { "total": 5.194419201989717, "count": 18199, "is_parallel": true, "self": 5.194419201989717 }, "communicator.exchange": { "total": 188.8105175200016, "count": 18199, "is_parallel": true, "self": 188.8105175200016 }, "steps_from_proto": { "total": 32.748411675000625, "count": 18199, "is_parallel": true, "self": 6.25296335699835, "children": { "_process_rank_one_or_two_observation": { "total": 26.495448318002275, "count": 181990, "is_parallel": true, "self": 26.495448318002275 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016041300000324554, "count": 1, "self": 0.00016041300000324554, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 451.1859919530266, "count": 471867, "is_parallel": true, "self": 9.620314552037598, "children": { "process_trajectory": { "total": 255.5112672909895, "count": 471867, "is_parallel": true, "self": 254.66407598098954, "children": { "RLTrainer._checkpoint": { "total": 0.847191309999971, "count": 4, "is_parallel": true, "self": 0.847191309999971 } } }, "_update_policy": { "total": 186.05441010999948, "count": 90, "is_parallel": true, "self": 54.210312709001016, "children": { "TorchPPOOptimizer.update": { "total": 131.84409740099846, "count": 4587, "is_parallel": true, "self": 131.84409740099846 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08268312200004857, "count": 1, "self": 0.001046135000024151, "children": { "RLTrainer._checkpoint": { "total": 0.08163698700002442, "count": 1, "self": 0.08163698700002442 } } } } } } }