{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9007925987243652, "min": 0.8750618696212769, "max": 2.8592350482940674, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8561.1328125, "min": 8561.1328125, "max": 29187.072265625, "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": 13.108366012573242, "min": 0.35139909386634827, "max": 13.108366012573242, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2556.13134765625, "min": 68.17142486572266, "max": 2660.91943359375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06759778913778171, "min": 0.0647307749430754, "max": 0.07377340359625853, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27039115655112683, "min": 0.2589230997723016, "max": 0.3688670179812927, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2005512816648857, "min": 0.11589212141766705, "max": 0.2877111409809075, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8022051266595428, "min": 0.4635684856706682, "max": 1.4385557049045374, "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": 25.59090909090909, "min": 3.2045454545454546, "max": 26.12727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 141.0, "max": 1437.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.2045454545454546, "max": 26.12727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 141.0, "max": 1437.0, "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": "1746388901", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746389339" }, "total": 437.26656823400003, "count": 1, "self": 0.4381613440000365, "children": { "run_training.setup": { "total": 0.021500408000065363, "count": 1, "self": 0.021500408000065363 }, "TrainerController.start_learning": { "total": 436.80690648199993, "count": 1, "self": 0.3867685409936712, "children": { "TrainerController._reset_env": { "total": 2.117723549999937, "count": 1, "self": 2.117723549999937 }, "TrainerController.advance": { "total": 434.2157234430065, "count": 18192, "self": 0.40587738003250706, "children": { "env_step": { "total": 311.35871067198445, "count": 18192, "self": 238.0757109969975, "children": { "SubprocessEnvManager._take_step": { "total": 73.05597614200701, "count": 18192, "self": 1.3321056410061374, "children": { "TorchPolicy.evaluate": { "total": 71.72387050100087, "count": 18192, "self": 71.72387050100087 } } }, "workers": { "total": 0.22702353297995614, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 435.3156339769871, "count": 18192, "is_parallel": true, "self": 227.07044327098902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023528650001480855, "count": 1, "is_parallel": true, "self": 0.0007303640011286916, "children": { "_process_rank_one_or_two_observation": { "total": 0.001622500999019394, "count": 10, "is_parallel": true, "self": 0.001622500999019394 } } }, "UnityEnvironment.step": { "total": 0.040875047000099585, "count": 1, "is_parallel": true, "self": 0.0005884219999643392, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043182100012018054, "count": 1, "is_parallel": true, "self": 0.00043182100012018054 }, "communicator.exchange": { "total": 0.038037312000142265, "count": 1, "is_parallel": true, "self": 0.038037312000142265 }, "steps_from_proto": { "total": 0.0018174919998728, "count": 1, "is_parallel": true, "self": 0.00034902499965028255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014684670002225175, "count": 10, "is_parallel": true, "self": 0.0014684670002225175 } } } } } } }, "UnityEnvironment.step": { "total": 208.24519070599808, "count": 18191, "is_parallel": true, "self": 9.830403416978015, "children": { "UnityEnvironment._generate_step_input": { "total": 5.453146399991738, "count": 18191, "is_parallel": true, "self": 5.453146399991738 }, "communicator.exchange": { "total": 160.41731675000142, "count": 18191, "is_parallel": true, "self": 160.41731675000142 }, "steps_from_proto": { "total": 32.54432413902691, "count": 18191, "is_parallel": true, "self": 5.955781979985886, "children": { "_process_rank_one_or_two_observation": { "total": 26.588542159041026, "count": 181910, "is_parallel": true, "self": 26.588542159041026 } } } } } } } } } } }, "trainer_advance": { "total": 122.45113539098952, "count": 18192, "self": 0.48742043798301893, "children": { "process_trajectory": { "total": 27.788689970006544, "count": 18192, "self": 27.33929299300644, "children": { "RLTrainer._checkpoint": { "total": 0.44939697700010584, "count": 4, "self": 0.44939697700010584 } } }, "_update_policy": { "total": 94.17502498299996, "count": 90, "self": 38.67821387699337, "children": { "TorchPPOOptimizer.update": { "total": 55.49681110600659, "count": 4587, "self": 55.49681110600659 } } } } } } }, "trainer_threads": { "total": 9.899999895424116e-07, "count": 1, "self": 9.899999895424116e-07 }, "TrainerController._save_models": { "total": 0.08668995799985169, "count": 1, "self": 0.001071389999879102, "children": { "RLTrainer._checkpoint": { "total": 0.08561856799997258, "count": 1, "self": 0.08561856799997258 } } } } } } }