{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.907357394695282, "min": 0.907357394695282, "max": 2.8555006980895996, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8683.41015625, "min": 8683.41015625, "max": 29274.59375, "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": 12.877532005310059, "min": 0.38565245270729065, "max": 12.877532005310059, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.11865234375, "min": 74.81657409667969, "max": 2579.642578125, "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": 0.06531170852008025, "min": 0.0625955390620648, "max": 0.07826770375712147, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.261246834080321, "min": 0.25670563574770794, "max": 0.3913385187856073, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18360373560412258, "min": 0.09476223315098597, "max": 0.2867168390867757, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7344149424164903, "min": 0.3790489326039439, "max": 1.4335841954338784, "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": 26.227272727272727, "min": 3.0454545454545454, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1154.0, "min": 134.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.227272727272727, "min": 3.0454545454545454, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1154.0, "min": 134.0, "max": 1390.0, "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": "1680805674", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/dung/.conda/envs/ml_agent/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu111", "numpy_version": "1.23.2", "end_time_seconds": "1680805901" }, "total": 226.4066539689993, "count": 1, "self": 0.2725929769985669, "children": { "run_training.setup": { "total": 0.01569502399979683, "count": 1, "self": 0.01569502399979683 }, "TrainerController.start_learning": { "total": 226.11836596800094, "count": 1, "self": 0.4253412241832848, "children": { "TrainerController._reset_env": { "total": 4.277209779000259, "count": 1, "self": 4.277209779000259 }, "TrainerController.advance": { "total": 221.32227128681734, "count": 18205, "self": 0.18429641292823362, "children": { "env_step": { "total": 221.1379748738891, "count": 18205, "self": 146.3273353290333, "children": { "SubprocessEnvManager._take_step": { "total": 74.6151823159762, "count": 18205, "self": 0.8760853799176402, "children": { "TorchPolicy.evaluate": { "total": 73.73909693605856, "count": 18205, "self": 11.726950304939237, "children": { "TorchPolicy.sample_actions": { "total": 62.01214663111932, "count": 18205, "self": 62.01214663111932 } } } } }, "workers": { "total": 0.19545722887960437, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 225.59947846183604, "count": 18205, "is_parallel": true, "self": 122.17532428983759, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.012335059998804354, "count": 1, "is_parallel": true, "self": 0.011528019997058436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008070400017459178, "count": 10, "is_parallel": true, "self": 0.0008070400017459178 } } }, "UnityEnvironment.step": { "total": 0.04097985099906509, "count": 1, "is_parallel": true, "self": 0.00030381699798454065, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022035999973013531, "count": 1, "is_parallel": true, "self": 0.00022035999973013531 }, "communicator.exchange": { "total": 0.03960793999976886, "count": 1, "is_parallel": true, "self": 0.03960793999976886 }, "steps_from_proto": { "total": 0.0008477340015815571, "count": 1, "is_parallel": true, "self": 0.00022272700152825564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006250070000533015, "count": 10, "is_parallel": true, "self": 0.0006250070000533015 } } } } } } }, "UnityEnvironment.step": { "total": 103.42415417199845, "count": 18204, "is_parallel": true, "self": 4.564147764962399, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6047035449373652, "count": 18204, "is_parallel": true, "self": 2.6047035449373652 }, "communicator.exchange": { "total": 83.18398581109614, "count": 18204, "is_parallel": true, "self": 83.18398581109614 }, "steps_from_proto": { "total": 13.071317051002552, "count": 18204, "is_parallel": true, "self": 3.1866120774484443, "children": { "_process_rank_one_or_two_observation": { "total": 9.884704973554108, "count": 182040, "is_parallel": true, "self": 9.884704973554108 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012410399904183578, "count": 1, "self": 0.00012410399904183578, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 221.0033483857078, "count": 170055, "is_parallel": true, "self": 1.8428706235663412, "children": { "process_trajectory": { "total": 122.14445705114667, "count": 170055, "is_parallel": true, "self": 121.5877537561446, "children": { "RLTrainer._checkpoint": { "total": 0.5567032950020803, "count": 4, "is_parallel": true, "self": 0.5567032950020803 } } }, "_update_policy": { "total": 97.01602071099478, "count": 90, "is_parallel": true, "self": 29.646479364939296, "children": { "TorchPPOOptimizer.update": { "total": 67.36954134605548, "count": 4587, "is_parallel": true, "self": 67.36954134605548 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09341957400101819, "count": 1, "self": 0.0007484200014005182, "children": { "RLTrainer._checkpoint": { "total": 0.09267115399961767, "count": 1, "self": 0.09267115399961767 } } } } } } }