{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9223756790161133, "min": 0.9223756790161133, "max": 2.859018325805664, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8847.427734375, "min": 8847.427734375, "max": 29342.10546875, "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": 12.624662399291992, "min": 0.5061714053153992, "max": 12.624662399291992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2461.80908203125, "min": 98.19725036621094, "max": 2551.27490234375, "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": 0.07169415483367272, "min": 0.06204715560249728, "max": 0.08011289363311531, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2867766193346909, "min": 0.24818862240998912, "max": 0.37300284392446936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21052181939868367, "min": 0.13447872669248861, "max": 0.27712104184662595, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8420872775947347, "min": 0.5379149067699545, "max": 1.3481865542776446, "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": 24.795454545454547, "min": 3.9318181818181817, "max": 25.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1091.0, "min": 173.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.795454545454547, "min": 3.9318181818181817, "max": 25.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1091.0, "min": 173.0, "max": 1375.0, "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": "1702720129", "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=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702720740" }, "total": 610.5202172039999, "count": 1, "self": 0.9480953329994009, "children": { "run_training.setup": { "total": 0.10011269700044068, "count": 1, "self": 0.10011269700044068 }, "TrainerController.start_learning": { "total": 609.472009174, "count": 1, "self": 0.8942528040615798, "children": { "TrainerController._reset_env": { "total": 4.545895813000243, "count": 1, "self": 4.545895813000243 }, "TrainerController.advance": { "total": 603.8825066679374, "count": 18212, "self": 0.45977918194057565, "children": { "env_step": { "total": 603.4227274859968, "count": 18212, "self": 467.5338484770391, "children": { "SubprocessEnvManager._take_step": { "total": 135.46575928202674, "count": 18212, "self": 2.6334233360275903, "children": { "TorchPolicy.evaluate": { "total": 132.83233594599915, "count": 18212, "self": 132.83233594599915 } } }, "workers": { "total": 0.4231197269309632, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 607.1854577430095, "count": 18212, "is_parallel": true, "self": 285.54198196203924, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00687206100064941, "count": 1, "is_parallel": true, "self": 0.004442725998160313, "children": { "_process_rank_one_or_two_observation": { "total": 0.002429335002489097, "count": 10, "is_parallel": true, "self": 0.002429335002489097 } } }, "UnityEnvironment.step": { "total": 0.047705627999675926, "count": 1, "is_parallel": true, "self": 0.0008328270005222294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044843799969385145, "count": 1, "is_parallel": true, "self": 0.00044843799969385145 }, "communicator.exchange": { "total": 0.044164619999719434, "count": 1, "is_parallel": true, "self": 0.044164619999719434 }, "steps_from_proto": { "total": 0.0022597429997404106, "count": 1, "is_parallel": true, "self": 0.0004483399989112513, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018114030008291593, "count": 10, "is_parallel": true, "self": 0.0018114030008291593 } } } } } } }, "UnityEnvironment.step": { "total": 321.6434757809702, "count": 18211, "is_parallel": true, "self": 15.894221095837565, "children": { "UnityEnvironment._generate_step_input": { "total": 7.770501947020421, "count": 18211, "is_parallel": true, "self": 7.770501947020421 }, "communicator.exchange": { "total": 251.7345734450164, "count": 18211, "is_parallel": true, "self": 251.7345734450164 }, "steps_from_proto": { "total": 46.24417929309584, "count": 18211, "is_parallel": true, "self": 9.160090650212624, "children": { "_process_rank_one_or_two_observation": { "total": 37.084088642883216, "count": 182110, "is_parallel": true, "self": 37.084088642883216 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016437600061181001, "count": 1, "self": 0.00016437600061181001, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 596.0163222854135, "count": 833015, "is_parallel": true, "self": 19.09220825032662, "children": { "process_trajectory": { "total": 319.6660335150855, "count": 833015, "is_parallel": true, "self": 318.5714111290863, "children": { "RLTrainer._checkpoint": { "total": 1.0946223859991733, "count": 4, "is_parallel": true, "self": 1.0946223859991733 } } }, "_update_policy": { "total": 257.2580805200014, "count": 90, "is_parallel": true, "self": 71.60802858398893, "children": { "TorchPPOOptimizer.update": { "total": 185.65005193601246, "count": 4587, "is_parallel": true, "self": 185.65005193601246 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14918951300023764, "count": 1, "self": 0.0020779410006070975, "children": { "RLTrainer._checkpoint": { "total": 0.14711157199963054, "count": 1, "self": 0.14711157199963054 } } } } } } }