{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0606619119644165, "min": 1.0606619119644165, "max": 2.86948299407959, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10150.5341796875, "min": 10150.5341796875, "max": 29386.375, "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": 12.642425537109375, "min": 0.2854849100112915, "max": 12.642425537109375, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2465.27294921875, "min": 55.384071350097656, "max": 2553.404296875, "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": 0.07097572925875498, "min": 0.06362749921196761, "max": 0.07470189863039801, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2839029170350199, "min": 0.26120908068625404, "max": 0.37350949315199006, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21457266157456473, "min": 0.10472005354548694, "max": 0.29706711991160517, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8582906462982589, "min": 0.41888021418194776, "max": 1.485335599558026, "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": 24.84090909090909, "min": 2.909090909090909, "max": 24.98181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 128.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 2.909090909090909, "max": 24.98181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 128.0, "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": "1709317050", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.2.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1709317741" }, "total": 691.6290685619997, "count": 1, "self": 0.6461348740003814, "children": { "run_training.setup": { "total": 0.11352936099956423, "count": 1, "self": 0.11352936099956423 }, "TrainerController.start_learning": { "total": 690.8694043269998, "count": 1, "self": 1.0438189379847245, "children": { "TrainerController._reset_env": { "total": 4.783314633000373, "count": 1, "self": 4.783314633000373 }, "TrainerController.advance": { "total": 684.9290372640144, "count": 18201, "self": 0.5122895780177714, "children": { "env_step": { "total": 684.4167476859966, "count": 18201, "self": 524.705447577935, "children": { "SubprocessEnvManager._take_step": { "total": 159.19355127495783, "count": 18201, "self": 3.123275029886827, "children": { "TorchPolicy.evaluate": { "total": 156.070276245071, "count": 18201, "self": 156.070276245071 } } }, "workers": { "total": 0.5177488331037239, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 688.5402811270169, "count": 18201, "is_parallel": true, "self": 321.3515986850198, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.011677520000375807, "count": 1, "is_parallel": true, "self": 0.005328867000571336, "children": { "_process_rank_one_or_two_observation": { "total": 0.006348652999804472, "count": 10, "is_parallel": true, "self": 0.006348652999804472 } } }, "UnityEnvironment.step": { "total": 0.05342904299959628, "count": 1, "is_parallel": true, "self": 0.0008168099993781652, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005339420004020212, "count": 1, "is_parallel": true, "self": 0.0005339420004020212 }, "communicator.exchange": { "total": 0.04927533099998982, "count": 1, "is_parallel": true, "self": 0.04927533099998982 }, "steps_from_proto": { "total": 0.002802959999826271, "count": 1, "is_parallel": true, "self": 0.0005277680011204211, "children": { "_process_rank_one_or_two_observation": { "total": 0.00227519199870585, "count": 10, "is_parallel": true, "self": 0.00227519199870585 } } } } } } }, "UnityEnvironment.step": { "total": 367.1886824419971, "count": 18200, "is_parallel": true, "self": 16.965768932072933, "children": { "UnityEnvironment._generate_step_input": { "total": 8.858108809009536, "count": 18200, "is_parallel": true, "self": 8.858108809009536 }, "communicator.exchange": { "total": 287.3933216648793, "count": 18200, "is_parallel": true, "self": 287.3933216648793 }, "steps_from_proto": { "total": 53.97148303603535, "count": 18200, "is_parallel": true, "self": 10.610679479919781, "children": { "_process_rank_one_or_two_observation": { "total": 43.36080355611557, "count": 182000, "is_parallel": true, "self": 43.36080355611557 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002734059999056626, "count": 1, "self": 0.0002734059999056626, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 676.7273954032453, "count": 937028, "is_parallel": true, "self": 21.091013145146462, "children": { "process_trajectory": { "total": 361.26163854310016, "count": 937028, "is_parallel": true, "self": 360.1525272150993, "children": { "RLTrainer._checkpoint": { "total": 1.1091113280008358, "count": 4, "is_parallel": true, "self": 1.1091113280008358 } } }, "_update_policy": { "total": 294.37474371499866, "count": 90, "is_parallel": true, "self": 91.01723748203221, "children": { "TorchPPOOptimizer.update": { "total": 203.35750623296644, "count": 4587, "is_parallel": true, "self": 203.35750623296644 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11296008600038476, "count": 1, "self": 0.0019843210002363776, "children": { "RLTrainer._checkpoint": { "total": 0.11097576500014839, "count": 1, "self": 0.11097576500014839 } } } } } } }