{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9406577944755554, "min": 0.9406577944755554, "max": 2.8538103103637695, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8991.748046875, "min": 8991.748046875, "max": 29194.478515625, "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": 12.185281753540039, "min": 0.3915165364742279, "max": 12.185281753540039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2376.1298828125, "min": 75.95420837402344, "max": 2457.1337890625, "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": 0.07372850632265338, "min": 0.060688515147251335, "max": 0.07577956500901172, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2949140252906135, "min": 0.24275406058900534, "max": 0.3670772639958231, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1982135792792428, "min": 0.13355729050989099, "max": 0.2738582117154318, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7928543171169712, "min": 0.5342291620395639, "max": 1.358946847565034, "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": 24.181818181818183, "min": 3.25, "max": 24.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1064.0, "min": 143.0, "max": 1316.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.181818181818183, "min": 3.25, "max": 24.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1064.0, "min": 143.0, "max": 1316.0, "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": "1690800697", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690801214" }, "total": 516.4151647890001, "count": 1, "self": 0.4361974520001013, "children": { "run_training.setup": { "total": 0.03713193900000533, "count": 1, "self": 0.03713193900000533 }, "TrainerController.start_learning": { "total": 515.941835398, "count": 1, "self": 0.6297648820070663, "children": { "TrainerController._reset_env": { "total": 5.39262473399998, "count": 1, "self": 5.39262473399998 }, "TrainerController.advance": { "total": 509.69833344699293, "count": 18214, "self": 0.2938659269979098, "children": { "env_step": { "total": 509.404467519995, "count": 18214, "self": 371.52762555698916, "children": { "SubprocessEnvManager._take_step": { "total": 137.5650374490051, "count": 18214, "self": 1.894946285008814, "children": { "TorchPolicy.evaluate": { "total": 135.6700911639963, "count": 18214, "self": 135.6700911639963 } } }, "workers": { "total": 0.31180451400075526, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 514.0073937639905, "count": 18214, "is_parallel": true, "self": 241.854772021001, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006775779000008697, "count": 1, "is_parallel": true, "self": 0.004479733999971813, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022960450000368837, "count": 10, "is_parallel": true, "self": 0.0022960450000368837 } } }, "UnityEnvironment.step": { "total": 0.08773697599997377, "count": 1, "is_parallel": true, "self": 0.010652371999924526, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040346200000840327, "count": 1, "is_parallel": true, "self": 0.00040346200000840327 }, "communicator.exchange": { "total": 0.07451964800003452, "count": 1, "is_parallel": true, "self": 0.07451964800003452 }, "steps_from_proto": { "total": 0.0021614940000063143, "count": 1, "is_parallel": true, "self": 0.0004017190000240589, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017597749999822554, "count": 10, "is_parallel": true, "self": 0.0017597749999822554 } } } } } } }, "UnityEnvironment.step": { "total": 272.15262174298954, "count": 18213, "is_parallel": true, "self": 11.3735743789901, "children": { "UnityEnvironment._generate_step_input": { "total": 5.795248841992247, "count": 18213, "is_parallel": true, "self": 5.795248841992247 }, "communicator.exchange": { "total": 215.24991176299494, "count": 18213, "is_parallel": true, "self": 215.24991176299494 }, "steps_from_proto": { "total": 39.73388675901225, "count": 18213, "is_parallel": true, "self": 7.583098650046168, "children": { "_process_rank_one_or_two_observation": { "total": 32.15078810896608, "count": 182130, "is_parallel": true, "self": 32.15078810896608 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001682690000279763, "count": 1, "self": 0.0001682690000279763, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 505.62176263902296, "count": 470167, "is_parallel": true, "self": 11.448621694023302, "children": { "process_trajectory": { "total": 281.2542586529992, "count": 470167, "is_parallel": true, "self": 279.08102355299917, "children": { "RLTrainer._checkpoint": { "total": 2.1732351000000563, "count": 4, "is_parallel": true, "self": 2.1732351000000563 } } }, "_update_policy": { "total": 212.91888229200043, "count": 90, "is_parallel": true, "self": 82.99744547100119, "children": { "TorchPPOOptimizer.update": { "total": 129.92143682099925, "count": 4587, "is_parallel": true, "self": 129.92143682099925 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22094406600001548, "count": 1, "self": 0.0009310130000130812, "children": { "RLTrainer._checkpoint": { "total": 0.2200130530000024, "count": 1, "self": 0.2200130530000024 } } } } } } }