{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9449869990348816, "min": 0.9449869990348816, "max": 2.8689353466033936, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9095.5, "min": 9095.5, "max": 29412.326171875, "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": 12.819543838500977, "min": 0.39099907875061035, "max": 12.861390113830566, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.81103515625, "min": 75.85382080078125, "max": 2623.7236328125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0695970101787323, "min": 0.06170151631830616, "max": 0.07407186244674058, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2783880407149292, "min": 0.25022194463135927, "max": 0.36160460356611523, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21208347405727002, "min": 0.10816111195120302, "max": 0.2952766600777121, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8483338962290801, "min": 0.4326444478048121, "max": 1.4763833003885605, "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": 24.59090909090909, "min": 3.159090909090909, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1082.0, "min": 139.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.59090909090909, "min": 3.159090909090909, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1082.0, "min": 139.0, "max": 1405.0, "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": "1687858290", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687858803" }, "total": 513.6758303870001, "count": 1, "self": 0.7028646839999055, "children": { "run_training.setup": { "total": 0.04385395799999969, "count": 1, "self": 0.04385395799999969 }, "TrainerController.start_learning": { "total": 512.9291117450002, "count": 1, "self": 0.5981341939482263, "children": { "TrainerController._reset_env": { "total": 5.132019250999747, "count": 1, "self": 5.132019250999747 }, "TrainerController.advance": { "total": 506.9294666510523, "count": 18222, "self": 0.2986240360573902, "children": { "env_step": { "total": 506.6308426149949, "count": 18222, "self": 367.7034021740201, "children": { "SubprocessEnvManager._take_step": { "total": 138.63764284197532, "count": 18222, "self": 1.9406870129996605, "children": { "TorchPolicy.evaluate": { "total": 136.69695582897566, "count": 18222, "self": 136.69695582897566 } } }, "workers": { "total": 0.28979759899948476, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 511.10244798402573, "count": 18222, "is_parallel": true, "self": 241.37572830302906, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005590407999989111, "count": 1, "is_parallel": true, "self": 0.004063442999722611, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015269650002665003, "count": 10, "is_parallel": true, "self": 0.0015269650002665003 } } }, "UnityEnvironment.step": { "total": 0.11055344099986542, "count": 1, "is_parallel": true, "self": 0.0007960370003274875, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047149700003501493, "count": 1, "is_parallel": true, "self": 0.00047149700003501493 }, "communicator.exchange": { "total": 0.10666594799977247, "count": 1, "is_parallel": true, "self": 0.10666594799977247 }, "steps_from_proto": { "total": 0.002619958999730443, "count": 1, "is_parallel": true, "self": 0.00048057199910545023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021393870006249927, "count": 10, "is_parallel": true, "self": 0.0021393870006249927 } } } } } } }, "UnityEnvironment.step": { "total": 269.72671968099667, "count": 18221, "is_parallel": true, "self": 11.114225148002333, "children": { "UnityEnvironment._generate_step_input": { "total": 5.997649679975439, "count": 18221, "is_parallel": true, "self": 5.997649679975439 }, "communicator.exchange": { "total": 212.76312773501013, "count": 18221, "is_parallel": true, "self": 212.76312773501013 }, "steps_from_proto": { "total": 39.851717118008764, "count": 18221, "is_parallel": true, "self": 7.343910983039677, "children": { "_process_rank_one_or_two_observation": { "total": 32.50780613496909, "count": 182210, "is_parallel": true, "self": 32.50780613496909 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014103500006967806, "count": 1, "self": 0.00014103500006967806, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 502.81352019074075, "count": 480993, "is_parallel": true, "self": 11.2137930217732, "children": { "process_trajectory": { "total": 278.20763534396747, "count": 480993, "is_parallel": true, "self": 275.961362792968, "children": { "RLTrainer._checkpoint": { "total": 2.2462725509994925, "count": 4, "is_parallel": true, "self": 2.2462725509994925 } } }, "_update_policy": { "total": 213.39209182500008, "count": 90, "is_parallel": true, "self": 81.97996295300436, "children": { "TorchPPOOptimizer.update": { "total": 131.41212887199572, "count": 4587, "is_parallel": true, "self": 131.41212887199572 } } } } } } } } }, "TrainerController._save_models": { "total": 0.26935061399990445, "count": 1, "self": 0.0015739019995635317, "children": { "RLTrainer._checkpoint": { "total": 0.2677767120003409, "count": 1, "self": 0.2677767120003409 } } } } } } }