{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.947270929813385, "min": 0.947270929813385, "max": 2.8660669326782227, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9054.962890625, "min": 9054.962890625, "max": 29382.91796875, "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": 12.564305305480957, "min": 0.194668248295784, "max": 12.564305305480957, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2450.03955078125, "min": 37.76564025878906, "max": 2557.814208984375, "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": 0.062143091459053244, "min": 0.062143091459053244, "max": 0.07371109535337846, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24857236583621298, "min": 0.24857236583621298, "max": 0.36855547676689226, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20259750988699643, "min": 0.14522319164483205, "max": 0.30550581866911813, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8103900395479857, "min": 0.5808927665793282, "max": 1.3894042074680328, "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": 24.977272727272727, "min": 3.2045454545454546, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 141.0, "max": 1352.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.2045454545454546, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 141.0, "max": 1352.0, "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": "1684204851", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684205318" }, "total": 467.255111885, "count": 1, "self": 0.7886120850001817, "children": { "run_training.setup": { "total": 0.062244463999945765, "count": 1, "self": 0.062244463999945765 }, "TrainerController.start_learning": { "total": 466.4042553359999, "count": 1, "self": 0.5479033309964052, "children": { "TrainerController._reset_env": { "total": 4.322356138000032, "count": 1, "self": 4.322356138000032 }, "TrainerController.advance": { "total": 461.3064357200036, "count": 18215, "self": 0.2668945109954848, "children": { "env_step": { "total": 461.0395412090081, "count": 18215, "self": 334.528049017003, "children": { "SubprocessEnvManager._take_step": { "total": 126.24945844999786, "count": 18215, "self": 1.8571761599901038, "children": { "TorchPolicy.evaluate": { "total": 124.39228229000776, "count": 18215, "self": 124.39228229000776 } } }, "workers": { "total": 0.2620337420072474, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 464.7729316579928, "count": 18215, "is_parallel": true, "self": 219.33592214699524, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006396928999947704, "count": 1, "is_parallel": true, "self": 0.004174625000132437, "children": { "_process_rank_one_or_two_observation": { "total": 0.002222303999815267, "count": 10, "is_parallel": true, "self": 0.002222303999815267 } } }, "UnityEnvironment.step": { "total": 0.04012005800007046, "count": 1, "is_parallel": true, "self": 0.0006741780001675579, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003299459999652754, "count": 1, "is_parallel": true, "self": 0.0003299459999652754 }, "communicator.exchange": { "total": 0.036723156999983075, "count": 1, "is_parallel": true, "self": 0.036723156999983075 }, "steps_from_proto": { "total": 0.002392776999954549, "count": 1, "is_parallel": true, "self": 0.0004303929998741296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019623840000804194, "count": 10, "is_parallel": true, "self": 0.0019623840000804194 } } } } } } }, "UnityEnvironment.step": { "total": 245.43700951099754, "count": 18214, "is_parallel": true, "self": 9.78165399399029, "children": { "UnityEnvironment._generate_step_input": { "total": 5.472994813996479, "count": 18214, "is_parallel": true, "self": 5.472994813996479 }, "communicator.exchange": { "total": 196.01338992200567, "count": 18214, "is_parallel": true, "self": 196.01338992200567 }, "steps_from_proto": { "total": 34.1689707810051, "count": 18214, "is_parallel": true, "self": 6.459452115017484, "children": { "_process_rank_one_or_two_observation": { "total": 27.709518665987616, "count": 182140, "is_parallel": true, "self": 27.709518665987616 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014421299988498504, "count": 1, "self": 0.00014421299988498504, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.5865521679783, "count": 432751, "is_parallel": true, "self": 10.075403689962172, "children": { "process_trajectory": { "total": 251.85748100001717, "count": 432751, "is_parallel": true, "self": 250.7658368730173, "children": { "RLTrainer._checkpoint": { "total": 1.0916441269998813, "count": 4, "is_parallel": true, "self": 1.0916441269998813 } } }, "_update_policy": { "total": 195.65366747799897, "count": 90, "is_parallel": true, "self": 71.1977996760038, "children": { "TorchPPOOptimizer.update": { "total": 124.45586780199517, "count": 4587, "is_parallel": true, "self": 124.45586780199517 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22741593399996418, "count": 1, "self": 0.0024172609998913686, "children": { "RLTrainer._checkpoint": { "total": 0.2249986730000728, "count": 1, "self": 0.2249986730000728 } } } } } } }