{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7650174498558044, "min": 0.7650174498558044, "max": 2.86189603805542, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7295.97119140625, "min": 7295.97119140625, "max": 29277.197265625, "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": 13.152483940124512, "min": 0.42055848240852356, "max": 13.208651542663574, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2564.734375, "min": 81.58834838867188, "max": 2694.56494140625, "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": 0.06605009992848614, "min": 0.06136266373291351, "max": 0.07768356836566133, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26420039971394454, "min": 0.24545065493165405, "max": 0.366282020734063, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2063604550910931, "min": 0.09801436457828637, "max": 0.27231240468282325, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8254418203643724, "min": 0.3920574583131455, "max": 1.3615620234141164, "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": 25.568181818181817, "min": 2.909090909090909, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 128.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 2.909090909090909, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 128.0, "max": 1418.0, "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": "1697074641", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697075123" }, "total": 482.00938708600006, "count": 1, "self": 0.4356087120000893, "children": { "run_training.setup": { "total": 0.04939126399995075, "count": 1, "self": 0.04939126399995075 }, "TrainerController.start_learning": { "total": 481.52438711, "count": 1, "self": 0.6771251950162878, "children": { "TrainerController._reset_env": { "total": 7.715523633000089, "count": 1, "self": 7.715523633000089 }, "TrainerController.advance": { "total": 473.04041786398375, "count": 18200, "self": 0.3132399529874874, "children": { "env_step": { "total": 472.72717791099626, "count": 18200, "self": 323.7379999099959, "children": { "SubprocessEnvManager._take_step": { "total": 148.6749016450143, "count": 18200, "self": 1.517585617023201, "children": { "TorchPolicy.evaluate": { "total": 147.1573160279911, "count": 18200, "self": 147.1573160279911 } } }, "workers": { "total": 0.31427635598606685, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 480.23081452099416, "count": 18200, "is_parallel": true, "self": 231.12122318201955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005703390999997282, "count": 1, "is_parallel": true, "self": 0.004277258000001893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014261329999953887, "count": 10, "is_parallel": true, "self": 0.0014261329999953887 } } }, "UnityEnvironment.step": { "total": 0.046063640000056694, "count": 1, "is_parallel": true, "self": 0.0006124510000518057, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032205599995904777, "count": 1, "is_parallel": true, "self": 0.00032205599995904777 }, "communicator.exchange": { "total": 0.04320745000006809, "count": 1, "is_parallel": true, "self": 0.04320745000006809 }, "steps_from_proto": { "total": 0.0019216829999777474, "count": 1, "is_parallel": true, "self": 0.00045597799987717735, "children": { "_process_rank_one_or_two_observation": { "total": 0.00146570500010057, "count": 10, "is_parallel": true, "self": 0.00146570500010057 } } } } } } }, "UnityEnvironment.step": { "total": 249.1095913389746, "count": 18199, "is_parallel": true, "self": 10.737168313999291, "children": { "UnityEnvironment._generate_step_input": { "total": 5.542091939983038, "count": 18199, "is_parallel": true, "self": 5.542091939983038 }, "communicator.exchange": { "total": 198.02543461598066, "count": 18199, "is_parallel": true, "self": 198.02543461598066 }, "steps_from_proto": { "total": 34.804896469011624, "count": 18199, "is_parallel": true, "self": 6.684244669988857, "children": { "_process_rank_one_or_two_observation": { "total": 28.120651799022767, "count": 181990, "is_parallel": true, "self": 28.120651799022767 } } } } } } } } } } } } }, "trainer_threads": { "total": 7.742599996163335e-05, "count": 1, "self": 7.742599996163335e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.27439788601873, "count": 499103, "is_parallel": true, "self": 10.435903008028049, "children": { "process_trajectory": { "total": 266.1127554089908, "count": 499103, "is_parallel": true, "self": 264.9786495799907, "children": { "RLTrainer._checkpoint": { "total": 1.1341058290000774, "count": 4, "is_parallel": true, "self": 1.1341058290000774 } } }, "_update_policy": { "total": 192.7257394689999, "count": 90, "is_parallel": true, "self": 59.22289592100867, "children": { "TorchPPOOptimizer.update": { "total": 133.50284354799123, "count": 4584, "is_parallel": true, "self": 133.50284354799123 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09124299199993402, "count": 1, "self": 0.0008798389999356004, "children": { "RLTrainer._checkpoint": { "total": 0.09036315299999842, "count": 1, "self": 0.09036315299999842 } } } } } } }