{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9843639731407166, "min": 0.9597277641296387, "max": 2.873669147491455, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9420.36328125, "min": 9329.2626953125, "max": 29460.85546875, "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": 12.701279640197754, "min": 0.3729843497276306, "max": 12.778619766235352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2476.74951171875, "min": 72.35896301269531, "max": 2606.83837890625, "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": 0.06757359773972912, "min": 0.06138117119096968, "max": 0.07411053699195014, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2702943909589165, "min": 0.2474746572167051, "max": 0.3596233244193261, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22879012104342966, "min": 0.1218975693256795, "max": 0.27920088398398135, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9151604841737186, "min": 0.487590277302718, "max": 1.3437554342489617, "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": 24.295454545454547, "min": 3.227272727272727, "max": 25.4, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1069.0, "min": 142.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.295454545454547, "min": 3.227272727272727, "max": 25.4, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1069.0, "min": 142.0, "max": 1397.0, "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": "1692615966", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692616438" }, "total": 472.00404998600015, "count": 1, "self": 0.7303827300002013, "children": { "run_training.setup": { "total": 0.04448683800001163, "count": 1, "self": 0.04448683800001163 }, "TrainerController.start_learning": { "total": 471.22918041799994, "count": 1, "self": 0.5532898770095471, "children": { "TrainerController._reset_env": { "total": 4.30529189799995, "count": 1, "self": 4.30529189799995 }, "TrainerController.advance": { "total": 466.13789341599045, "count": 18216, "self": 0.2782740749739787, "children": { "env_step": { "total": 465.85961934101647, "count": 18216, "self": 337.55171985299035, "children": { "SubprocessEnvManager._take_step": { "total": 128.01750824201804, "count": 18216, "self": 1.7699496760235434, "children": { "TorchPolicy.evaluate": { "total": 126.2475585659945, "count": 18216, "self": 126.2475585659945 } } }, "workers": { "total": 0.29039124600808464, "count": 18216, "self": 0.0, "children": { "worker_root": { "total": 469.5288537590143, "count": 18216, "is_parallel": true, "self": 220.39458589001606, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005951429000106145, "count": 1, "is_parallel": true, "self": 0.004175406000740622, "children": { "_process_rank_one_or_two_observation": { "total": 0.001776022999365523, "count": 10, "is_parallel": true, "self": 0.001776022999365523 } } }, "UnityEnvironment.step": { "total": 0.03581019099988225, "count": 1, "is_parallel": true, "self": 0.0006743169999481324, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033129899998129986, "count": 1, "is_parallel": true, "self": 0.00033129899998129986 }, "communicator.exchange": { "total": 0.03249659499988411, "count": 1, "is_parallel": true, "self": 0.03249659499988411 }, "steps_from_proto": { "total": 0.00230798000006871, "count": 1, "is_parallel": true, "self": 0.00038836499970784644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019196150003608636, "count": 10, "is_parallel": true, "self": 0.0019196150003608636 } } } } } } }, "UnityEnvironment.step": { "total": 249.13426786899822, "count": 18215, "is_parallel": true, "self": 10.452498052007286, "children": { "UnityEnvironment._generate_step_input": { "total": 5.307168168975977, "count": 18215, "is_parallel": true, "self": 5.307168168975977 }, "communicator.exchange": { "total": 197.41288925400863, "count": 18215, "is_parallel": true, "self": 197.41288925400863 }, "steps_from_proto": { "total": 35.96171239400633, "count": 18215, "is_parallel": true, "self": 6.480403759045885, "children": { "_process_rank_one_or_two_observation": { "total": 29.481308634960442, "count": 182150, "is_parallel": true, "self": 29.481308634960442 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015001899987510114, "count": 1, "self": 0.00015001899987510114, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 462.50627255311406, "count": 447043, "is_parallel": true, "self": 9.962794332056319, "children": { "process_trajectory": { "total": 254.45061482505662, "count": 447043, "is_parallel": true, "self": 252.73822479405658, "children": { "RLTrainer._checkpoint": { "total": 1.7123900310000408, "count": 4, "is_parallel": true, "self": 1.7123900310000408 } } }, "_update_policy": { "total": 198.09286339600112, "count": 90, "is_parallel": true, "self": 77.34579083201334, "children": { "TorchPPOOptimizer.update": { "total": 120.74707256398779, "count": 4587, "is_parallel": true, "self": 120.74707256398779 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23255520800012164, "count": 1, "self": 0.0011481760000151553, "children": { "RLTrainer._checkpoint": { "total": 0.23140703200010648, "count": 1, "self": 0.23140703200010648 } } } } } } }