{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8933303356170654, "min": 0.8894324898719788, "max": 2.8754124641418457, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8558.998046875, "min": 8558.998046875, "max": 29415.470703125, "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": 12.852367401123047, "min": 0.37865006923675537, "max": 12.852367401123047, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2506.211669921875, "min": 73.45811462402344, "max": 2606.0537109375, "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": 0.06531085016225309, "min": 0.061258819479353764, "max": 0.0733405908328731, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26124340064901236, "min": 0.24714448274971798, "max": 0.3637029610546569, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19526252950377324, "min": 0.10034655702218194, "max": 0.2878183049021983, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7810501180150929, "min": 0.40138622808872776, "max": 1.3782681375741959, "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": 25.65909090909091, "min": 2.9318181818181817, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 129.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 2.9318181818181817, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 129.0, "max": 1374.0, "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": "1679534035", "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", "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": "1679534528" }, "total": 492.4944630069999, "count": 1, "self": 0.7256343609997202, "children": { "run_training.setup": { "total": 0.16040952200000902, "count": 1, "self": 0.16040952200000902 }, "TrainerController.start_learning": { "total": 491.6084191240002, "count": 1, "self": 0.613223008004752, "children": { "TrainerController._reset_env": { "total": 6.851809575000061, "count": 1, "self": 6.851809575000061 }, "TrainerController.advance": { "total": 483.9184725479954, "count": 18216, "self": 0.3040194070067628, "children": { "env_step": { "total": 483.61445314098864, "count": 18216, "self": 347.7281631609749, "children": { "SubprocessEnvManager._take_step": { "total": 135.40545433700936, "count": 18216, "self": 2.720488033991387, "children": { "TorchPolicy.evaluate": { "total": 132.68496630301797, "count": 18216, "self": 132.68496630301797 } } }, "workers": { "total": 0.4808356430044114, "count": 18216, "self": 0.0, "children": { "worker_root": { "total": 490.0070041760023, "count": 18216, "is_parallel": true, "self": 233.83613948900802, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025107789997491636, "count": 1, "is_parallel": true, "self": 0.0007152989992391667, "children": { "_process_rank_one_or_two_observation": { "total": 0.001795480000509997, "count": 10, "is_parallel": true, "self": 0.001795480000509997 } } }, "UnityEnvironment.step": { "total": 0.04740100600020014, "count": 1, "is_parallel": true, "self": 0.0006019440002091869, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003306660000816919, "count": 1, "is_parallel": true, "self": 0.0003306660000816919 }, "communicator.exchange": { "total": 0.0443890769997779, "count": 1, "is_parallel": true, "self": 0.0443890769997779 }, "steps_from_proto": { "total": 0.0020793190001313633, "count": 1, "is_parallel": true, "self": 0.00042749800104502356, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016518209990863397, "count": 10, "is_parallel": true, "self": 0.0016518209990863397 } } } } } } }, "UnityEnvironment.step": { "total": 256.17086468699426, "count": 18215, "is_parallel": true, "self": 9.923921629967936, "children": { "UnityEnvironment._generate_step_input": { "total": 5.534492772992053, "count": 18215, "is_parallel": true, "self": 5.534492772992053 }, "communicator.exchange": { "total": 206.6695597270118, "count": 18215, "is_parallel": true, "self": 206.6695597270118 }, "steps_from_proto": { "total": 34.042890557022474, "count": 18215, "is_parallel": true, "self": 6.954006208087776, "children": { "_process_rank_one_or_two_observation": { "total": 27.088884348934698, "count": 182150, "is_parallel": true, "self": 27.088884348934698 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011494099999254104, "count": 1, "self": 0.00011494099999254104, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 480.1586630969964, "count": 435886, "is_parallel": true, "self": 11.346350659002837, "children": { "process_trajectory": { "total": 267.6527174019966, "count": 435886, "is_parallel": true, "self": 266.4734349449968, "children": { "RLTrainer._checkpoint": { "total": 1.179282456999772, "count": 4, "is_parallel": true, "self": 1.179282456999772 } } }, "_update_policy": { "total": 201.15959503599697, "count": 90, "is_parallel": true, "self": 72.53708653797139, "children": { "TorchPPOOptimizer.update": { "total": 128.62250849802558, "count": 4587, "is_parallel": true, "self": 128.62250849802558 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2247990519999803, "count": 1, "self": 0.0013896099999328726, "children": { "RLTrainer._checkpoint": { "total": 0.22340944200004742, "count": 1, "self": 0.22340944200004742 } } } } } } }