{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8530005812644958, "min": 0.8383908271789551, "max": 2.8597514629364014, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8181.9814453125, "min": 8181.9814453125, "max": 29412.544921875, "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": 12.994338035583496, "min": 0.3498460352420807, "max": 12.994338035583496, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.89599609375, "min": 67.87013244628906, "max": 2642.72216796875, "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": 0.06223158143064425, "min": 0.060812713811673365, "max": 0.07528247802567385, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.248926325722577, "min": 0.24325085524669346, "max": 0.35585015027683375, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2028043196335727, "min": 0.15784910019354748, "max": 0.2775503422553633, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8112172785342908, "min": 0.6313964007741899, "max": 1.3480203987336625, "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": 25.022727272727273, "min": 4.0, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 176.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 4.0, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 176.0, "max": 1421.0, "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": "1675530610", "python_version": "3.8.0 (default, Nov 6 2019, 21:49:08) \n[GCC 7.3.0]", "command_line_arguments": "/home/sebas/miniconda3/envs/RL-unity/bin/mlagents-learn --force ./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+cu102", "numpy_version": "1.19.0", "end_time_seconds": "1675530909" }, "total": 299.91092531755567, "count": 1, "self": 0.21797498874366283, "children": { "run_training.setup": { "total": 0.00751890242099762, "count": 1, "self": 0.00751890242099762 }, "TrainerController.start_learning": { "total": 299.685431426391, "count": 1, "self": 0.36140776984393597, "children": { "TrainerController._reset_env": { "total": 2.365686181001365, "count": 1, "self": 2.365686181001365 }, "TrainerController.advance": { "total": 296.8841963307932, "count": 18207, "self": 0.17374430503696203, "children": { "env_step": { "total": 296.71045202575624, "count": 18207, "self": 190.32740950025618, "children": { "SubprocessEnvManager._take_step": { "total": 106.20714913215488, "count": 18207, "self": 0.7967873672023416, "children": { "TorchPolicy.evaluate": { "total": 105.41036176495254, "count": 18207, "self": 26.120511693879962, "children": { "TorchPolicy.sample_actions": { "total": 79.28985007107258, "count": 18207, "self": 79.28985007107258 } } } } }, "workers": { "total": 0.17589339334517717, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 299.18588510062546, "count": 18207, "is_parallel": true, "self": 160.10110856033862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001365874893963337, "count": 1, "is_parallel": true, "self": 0.00028860103338956833, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010772738605737686, "count": 10, "is_parallel": true, "self": 0.0010772738605737686 } } }, "UnityEnvironment.step": { "total": 0.02300876472145319, "count": 1, "is_parallel": true, "self": 0.00021002814173698425, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016913656145334244, "count": 1, "is_parallel": true, "self": 0.00016913656145334244 }, "communicator.exchange": { "total": 0.021501419134438038, "count": 1, "is_parallel": true, "self": 0.021501419134438038 }, "steps_from_proto": { "total": 0.0011281808838248253, "count": 1, "is_parallel": true, "self": 0.00017351005226373672, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009546708315610886, "count": 10, "is_parallel": true, "self": 0.0009546708315610886 } } } } } } }, "UnityEnvironment.step": { "total": 139.08477654028684, "count": 18206, "is_parallel": true, "self": 6.583071378059685, "children": { "UnityEnvironment._generate_step_input": { "total": 2.8856508200988173, "count": 18206, "is_parallel": true, "self": 2.8856508200988173 }, "communicator.exchange": { "total": 99.14944237656891, "count": 18206, "is_parallel": true, "self": 99.14944237656891 }, "steps_from_proto": { "total": 30.466611965559423, "count": 18206, "is_parallel": true, "self": 3.468739408068359, "children": { "_process_rank_one_or_two_observation": { "total": 26.997872557491064, "count": 182060, "is_parallel": true, "self": 26.997872557491064 } } } } } } } } } } } } }, "trainer_threads": { "total": 7.236376404762268e-05, "count": 1, "self": 7.236376404762268e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 296.3658159058541, "count": 215031, "is_parallel": true, "self": 1.9880123194307089, "children": { "process_trajectory": { "total": 169.6373036596924, "count": 215031, "is_parallel": true, "self": 169.10059734247625, "children": { "RLTrainer._checkpoint": { "total": 0.5367063172161579, "count": 4, "is_parallel": true, "self": 0.5367063172161579 } } }, "_update_policy": { "total": 124.74049992673099, "count": 90, "is_parallel": true, "self": 34.31474053487182, "children": { "TorchPPOOptimizer.update": { "total": 90.42575939185917, "count": 4587, "is_parallel": true, "self": 90.42575939185917 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07406878098845482, "count": 1, "self": 0.00043107569217681885, "children": { "RLTrainer._checkpoint": { "total": 0.073637705296278, "count": 1, "self": 0.073637705296278 } } } } } } }