{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9651990532875061, "min": 0.9651990532875061, "max": 2.8370742797851562, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9173.251953125, "min": 9173.251953125, "max": 28960.853515625, "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": 12.841617584228516, "min": 0.4181671142578125, "max": 12.841617584228516, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2504.115478515625, "min": 81.12442016601562, "max": 2587.78466796875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07059431290069958, "min": 0.06529972196930982, "max": 0.0743190680504959, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2823772516027983, "min": 0.26127441264757445, "max": 0.37159534025247953, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19891976207202555, "min": 0.1632725757103888, "max": 0.28967822978601737, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7956790482881022, "min": 0.6530903028415552, "max": 1.4116038490159841, "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.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.Environment.CumulativeReward.mean": { "value": 25.65909090909091, "min": 4.136363636363637, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 182.0, "max": 1385.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 4.136363636363637, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 182.0, "max": 1385.0, "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": "1764318978", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/jay/anaconda3/envs/huggingface-rl/bin/mlagents-learn /home/jay/Workspace/tmp/huggingface-rl-course/Unit 5/ml-agents/config/ppo/SnowballTarget.yaml --env=/home/jay/Workspace/tmp/huggingface-rl-course/Unit 5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1764319229" }, "total": 251.0172137329355, "count": 1, "self": 0.21867214585654438, "children": { "run_training.setup": { "total": 0.03736178204417229, "count": 1, "self": 0.03736178204417229 }, "TrainerController.start_learning": { "total": 250.76117980503477, "count": 1, "self": 0.3402833722066134, "children": { "TrainerController._reset_env": { "total": 1.3183357261586934, "count": 1, "self": 1.3183357261586934 }, "TrainerController.advance": { "total": 249.04879971337505, "count": 18192, "self": 0.2940563808660954, "children": { "env_step": { "total": 174.4203592147678, "count": 18192, "self": 124.30676860641688, "children": { "SubprocessEnvManager._take_step": { "total": 49.89957783208229, "count": 18192, "self": 0.8160246859770268, "children": { "TorchPolicy.evaluate": { "total": 49.08355314610526, "count": 18192, "self": 49.08355314610526 } } }, "workers": { "total": 0.21401277626864612, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 250.21686017722823, "count": 18192, "is_parallel": true, "self": 144.4161773060914, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018278141506016254, "count": 1, "is_parallel": true, "self": 0.0005005907732993364, "children": { "_process_rank_one_or_two_observation": { "total": 0.001327223377302289, "count": 10, "is_parallel": true, "self": 0.001327223377302289 } } }, "UnityEnvironment.step": { "total": 0.016814162954688072, "count": 1, "is_parallel": true, "self": 0.0002459969837218523, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002355880569666624, "count": 1, "is_parallel": true, "self": 0.0002355880569666624 }, "communicator.exchange": { "total": 0.015490948921069503, "count": 1, "is_parallel": true, "self": 0.015490948921069503 }, "steps_from_proto": { "total": 0.0008416289929300547, "count": 1, "is_parallel": true, "self": 0.0001703950110822916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006712339818477631, "count": 10, "is_parallel": true, "self": 0.0006712339818477631 } } } } } } }, "UnityEnvironment.step": { "total": 105.80068287113681, "count": 18191, "is_parallel": true, "self": 4.412691375473514, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6946435859426856, "count": 18191, "is_parallel": true, "self": 2.6946435859426856 }, "communicator.exchange": { "total": 85.65649812365882, "count": 18191, "is_parallel": true, "self": 85.65649812365882 }, "steps_from_proto": { "total": 13.036849786061794, "count": 18191, "is_parallel": true, "self": 2.8609338770620525, "children": { "_process_rank_one_or_two_observation": { "total": 10.175915908999741, "count": 181910, "is_parallel": true, "self": 10.175915908999741 } } } } } } } } } } }, "trainer_advance": { "total": 74.33438411774114, "count": 18192, "self": 0.45447905524633825, "children": { "process_trajectory": { "total": 17.546561846975237, "count": 18192, "self": 17.305554494727403, "children": { "RLTrainer._checkpoint": { "total": 0.2410073522478342, "count": 4, "self": 0.2410073522478342 } } }, "_update_policy": { "total": 56.33334321551956, "count": 90, "self": 21.78431274695322, "children": { "TorchPPOOptimizer.update": { "total": 34.54903046856634, "count": 4587, "self": 34.54903046856634 } } } } } } }, "trainer_threads": { "total": 5.811452865600586e-07, "count": 1, "self": 5.811452865600586e-07 }, "TrainerController._save_models": { "total": 0.0537604121491313, "count": 1, "self": 0.0010421399492770433, "children": { "RLTrainer._checkpoint": { "total": 0.052718272199854255, "count": 1, "self": 0.052718272199854255 } } } } } } }