{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.6674165725708008, "min": 1.6674165725708008, "max": 2.8726658821105957, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 17149.37890625, "min": 16812.21875, "max": 29450.5703125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.511493682861328, "min": 0.21141324937343597, "max": 8.511493682861328, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1736.3447265625, "min": 41.0141716003418, "max": 1736.3447265625, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07407127405759621, "min": 0.06269844453077786, "max": 0.07424045011013695, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3703563702879811, "min": 0.25079377812311143, "max": 0.3712022505506848, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2519307076346641, "min": 0.11993663520871789, "max": 0.2629640838679145, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2596535381733203, "min": 0.47974654083487156, "max": 1.3148204193395725, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 18.163636363636364, "min": 3.0, "max": 18.163636363636364, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 999.0, "min": 132.0, "max": 999.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 18.163636363636364, "min": 3.0, "max": 18.163636363636364, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 999.0, "min": 132.0, "max": 999.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713966453", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --force --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": "1.23.5", "end_time_seconds": "1713966707" }, "total": 254.176483911, "count": 1, "self": 0.47630597599993507, "children": { "run_training.setup": { "total": 0.0513495510000439, "count": 1, "self": 0.0513495510000439 }, "TrainerController.start_learning": { "total": 253.648828384, "count": 1, "self": 0.34044086899211834, "children": { "TrainerController._reset_env": { "total": 2.5326383760000226, "count": 1, "self": 2.5326383760000226 }, "TrainerController.advance": { "total": 250.66475127000774, "count": 9133, "self": 0.14856226601239086, "children": { "env_step": { "total": 250.51618900399535, "count": 9133, "self": 164.10457999100026, "children": { "SubprocessEnvManager._take_step": { "total": 86.25721777599256, "count": 9133, "self": 0.8278512929890667, "children": { "TorchPolicy.evaluate": { "total": 85.42936648300349, "count": 9133, "self": 85.42936648300349 } } }, "workers": { "total": 0.15439123700252821, "count": 9133, "self": 0.0, "children": { "worker_root": { "total": 252.86213208799802, "count": 9133, "is_parallel": true, "self": 126.07234265299383, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00247228900002483, "count": 1, "is_parallel": true, "self": 0.0006633030000102735, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018089860000145563, "count": 10, "is_parallel": true, "self": 0.0018089860000145563 } } }, "UnityEnvironment.step": { "total": 0.10706960499999241, "count": 1, "is_parallel": true, "self": 0.0007301959999495011, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043499800005974976, "count": 1, "is_parallel": true, "self": 0.00043499800005974976 }, "communicator.exchange": { "total": 0.10372938499995144, "count": 1, "is_parallel": true, "self": 0.10372938499995144 }, "steps_from_proto": { "total": 0.002175026000031721, "count": 1, "is_parallel": true, "self": 0.00038375400004042604, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017912719999912952, "count": 10, "is_parallel": true, "self": 0.0017912719999912952 } } } } } } }, "UnityEnvironment.step": { "total": 126.7897894350042, "count": 9132, "is_parallel": true, "self": 5.5900285489958605, "children": { "UnityEnvironment._generate_step_input": { "total": 3.0259422640011735, "count": 9132, "is_parallel": true, "self": 3.0259422640011735 }, "communicator.exchange": { "total": 98.73923648800962, "count": 9132, "is_parallel": true, "self": 98.73923648800962 }, "steps_from_proto": { "total": 19.434582133997537, "count": 9132, "is_parallel": true, "self": 3.744087799983731, "children": { "_process_rank_one_or_two_observation": { "total": 15.690494334013806, "count": 91320, "is_parallel": true, "self": 15.690494334013806 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003835940000271876, "count": 1, "self": 0.0003835940000271876, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 247.46827170501456, "count": 365875, "is_parallel": true, "self": 8.24656985604804, "children": { "process_trajectory": { "total": 137.55758802696607, "count": 365875, "is_parallel": true, "self": 136.97415441896612, "children": { "RLTrainer._checkpoint": { "total": 0.5834336079999503, "count": 2, "is_parallel": true, "self": 0.5834336079999503 } } }, "_update_policy": { "total": 101.66411382200044, "count": 45, "is_parallel": true, "self": 32.72284590599986, "children": { "TorchPPOOptimizer.update": { "total": 68.94126791600058, "count": 2289, "is_parallel": true, "self": 68.94126791600058 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11061427500010268, "count": 1, "self": 0.001597230000129457, "children": { "RLTrainer._checkpoint": { "total": 0.10901704499997322, "count": 1, "self": 0.10901704499997322 } } } } } } }