{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9349887371063232, "min": 0.9349887371063232, "max": 2.86578106880188, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8958.126953125, "min": 8958.126953125, "max": 29316.94140625, "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": 12.817339897155762, "min": 0.3916582763195038, "max": 12.817339897155762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.38134765625, "min": 75.98170471191406, "max": 2580.39306640625, "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": 0.07777946388780359, "min": 0.060810724556373034, "max": 0.07777946388780359, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.31111785555121435, "min": 0.24324289822549214, "max": 0.3672298461144023, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1925424508312169, "min": 0.11864992202597432, "max": 0.2714734789787554, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7701698033248676, "min": 0.4745996881038973, "max": 1.357367394893777, "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": 25.636363636363637, "min": 3.0454545454545454, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 134.0, "max": 1383.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.0454545454545454, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 134.0, "max": 1383.0, "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": "1679657742", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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 --force", "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": "1679658189" }, "total": 447.01575971400007, "count": 1, "self": 0.38171983699999146, "children": { "run_training.setup": { "total": 0.09282672199992703, "count": 1, "self": 0.09282672199992703 }, "TrainerController.start_learning": { "total": 446.54121315500015, "count": 1, "self": 0.7064426490314872, "children": { "TrainerController._reset_env": { "total": 8.207988385999897, "count": 1, "self": 8.207988385999897 }, "TrainerController.advance": { "total": 437.5265634579689, "count": 18204, "self": 0.33905154494641465, "children": { "env_step": { "total": 437.1875119130225, "count": 18204, "self": 349.211904508064, "children": { "SubprocessEnvManager._take_step": { "total": 87.6406059589849, "count": 18204, "self": 2.4426679509901987, "children": { "TorchPolicy.evaluate": { "total": 85.19793800799471, "count": 18204, "self": 85.19793800799471 } } }, "workers": { "total": 0.33500144597360304, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 445.065719505008, "count": 18204, "is_parallel": true, "self": 207.5725325160122, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006716329000028054, "count": 1, "is_parallel": true, "self": 0.004996949000542372, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017193799994856818, "count": 10, "is_parallel": true, "self": 0.0017193799994856818 } } }, "UnityEnvironment.step": { "total": 0.03719492599998375, "count": 1, "is_parallel": true, "self": 0.0005376789997626474, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000361590000011347, "count": 1, "is_parallel": true, "self": 0.000361590000011347 }, "communicator.exchange": { "total": 0.03450141700000131, "count": 1, "is_parallel": true, "self": 0.03450141700000131 }, "steps_from_proto": { "total": 0.0017942400002084469, "count": 1, "is_parallel": true, "self": 0.00036814000009144365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014261000001170032, "count": 10, "is_parallel": true, "self": 0.0014261000001170032 } } } } } } }, "UnityEnvironment.step": { "total": 237.49318698899583, "count": 18203, "is_parallel": true, "self": 9.289915454959555, "children": { "UnityEnvironment._generate_step_input": { "total": 5.525150861016073, "count": 18203, "is_parallel": true, "self": 5.525150861016073 }, "communicator.exchange": { "total": 192.95473750799442, "count": 18203, "is_parallel": true, "self": 192.95473750799442 }, "steps_from_proto": { "total": 29.72338316502578, "count": 18203, "is_parallel": true, "self": 6.108196971105826, "children": { "_process_rank_one_or_two_observation": { "total": 23.615186193919953, "count": 182030, "is_parallel": true, "self": 23.615186193919953 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00036769999996977276, "count": 1, "self": 0.00036769999996977276, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 434.3365199750133, "count": 439133, "is_parallel": true, "self": 9.72625842998309, "children": { "process_trajectory": { "total": 240.83721165003044, "count": 439133, "is_parallel": true, "self": 240.21178666603032, "children": { "RLTrainer._checkpoint": { "total": 0.6254249840001194, "count": 4, "is_parallel": true, "self": 0.6254249840001194 } } }, "_update_policy": { "total": 183.77304989499976, "count": 90, "is_parallel": true, "self": 49.881817683998406, "children": { "TorchPPOOptimizer.update": { "total": 133.89123221100135, "count": 4587, "is_parallel": true, "self": 133.89123221100135 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0998509619998913, "count": 1, "self": 0.0007045299998935661, "children": { "RLTrainer._checkpoint": { "total": 0.09914643199999773, "count": 1, "self": 0.09914643199999773 } } } } } } }