{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0069396495819092, "min": 1.0069396495819092, "max": 2.810028076171875, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9614.259765625, "min": 9614.259765625, "max": 28808.408203125, "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": 12.656725883483887, "min": 0.31081098318099976, "max": 12.656725883483887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2468.0615234375, "min": 60.297332763671875, "max": 2568.51611328125, "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": 0.06861288506586467, "min": 0.057799714654524284, "max": 0.0758767314015559, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2744515402634587, "min": 0.23119885861809714, "max": 0.36978030635623776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23546830710827138, "min": 0.1087834547700671, "max": 0.281679127146216, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9418732284330855, "min": 0.4351338190802684, "max": 1.4048231445691166, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.616409730600001e-05, "min": 1.616409730600001e-05, "max": 0.0005837640027059999, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.465638922400003e-05, "min": 6.465638922400003e-05, "max": 0.00277032003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10538800000000001, "min": 0.10538800000000001, "max": 0.29458799999999996, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.42155200000000004, "min": 0.42155200000000004, "max": 1.42344, "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": 24.681818181818183, "min": 3.1136363636363638, "max": 24.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1086.0, "min": 137.0, "max": 1373.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.681818181818183, "min": 3.1136363636363638, "max": 24.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1086.0, "min": 137.0, "max": 1373.0, "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": "1716710688", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716711189" }, "total": 500.79940837000004, "count": 1, "self": 0.47871936000046844, "children": { "run_training.setup": { "total": 0.05563367099966854, "count": 1, "self": 0.05563367099966854 }, "TrainerController.start_learning": { "total": 500.2650553389999, "count": 1, "self": 0.7109024630158274, "children": { "TrainerController._reset_env": { "total": 2.115907714000059, "count": 1, "self": 2.115907714000059 }, "TrainerController.advance": { "total": 497.35660923498426, "count": 18200, "self": 0.3631436589657824, "children": { "env_step": { "total": 496.9934655760185, "count": 18200, "self": 326.54533360395635, "children": { "SubprocessEnvManager._take_step": { "total": 170.0980387850159, "count": 18200, "self": 1.7037756250006169, "children": { "TorchPolicy.evaluate": { "total": 168.39426316001527, "count": 18200, "self": 168.39426316001527 } } }, "workers": { "total": 0.35009318704624093, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 498.7785037659978, "count": 18200, "is_parallel": true, "self": 243.94271257897435, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002219015999799012, "count": 1, "is_parallel": true, "self": 0.0006655649990534585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015534510007455538, "count": 10, "is_parallel": true, "self": 0.0015534510007455538 } } }, "UnityEnvironment.step": { "total": 0.06019268000000011, "count": 1, "is_parallel": true, "self": 0.0007173359999796958, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004115980000278796, "count": 1, "is_parallel": true, "self": 0.0004115980000278796 }, "communicator.exchange": { "total": 0.05698251200010418, "count": 1, "is_parallel": true, "self": 0.05698251200010418 }, "steps_from_proto": { "total": 0.0020812339998883544, "count": 1, "is_parallel": true, "self": 0.00039561100038554287, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016856229995028116, "count": 10, "is_parallel": true, "self": 0.0016856229995028116 } } } } } } }, "UnityEnvironment.step": { "total": 254.83579118702346, "count": 18199, "is_parallel": true, "self": 11.347686508004244, "children": { "UnityEnvironment._generate_step_input": { "total": 6.006531404995712, "count": 18199, "is_parallel": true, "self": 6.006531404995712 }, "communicator.exchange": { "total": 200.15692748401852, "count": 18199, "is_parallel": true, "self": 200.15692748401852 }, "steps_from_proto": { "total": 37.32464579000498, "count": 18199, "is_parallel": true, "self": 7.39685486497774, "children": { "_process_rank_one_or_two_observation": { "total": 29.92779092502724, "count": 181990, "is_parallel": true, "self": 29.92779092502724 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013762099979430786, "count": 1, "self": 0.00013762099979430786, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 491.2628267113032, "count": 711357, "is_parallel": true, "self": 15.55820723330362, "children": { "process_trajectory": { "total": 275.542963600999, "count": 711357, "is_parallel": true, "self": 275.0221872739994, "children": { "RLTrainer._checkpoint": { "total": 0.5207763269995667, "count": 4, "is_parallel": true, "self": 0.5207763269995667 } } }, "_update_policy": { "total": 200.1616558770006, "count": 90, "is_parallel": true, "self": 62.33664410699612, "children": { "TorchPPOOptimizer.update": { "total": 137.8250117700045, "count": 4587, "is_parallel": true, "self": 137.8250117700045 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08149830599995767, "count": 1, "self": 0.0008183389995792822, "children": { "RLTrainer._checkpoint": { "total": 0.08067996700037838, "count": 1, "self": 0.08067996700037838 } } } } } } }