{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8018399477005005, "min": 0.8018399477005005, "max": 2.853074789047241, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7620.68701171875, "min": 7620.68701171875, "max": 29124.1875, "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": 13.053502082824707, "min": 0.33232054114341736, "max": 13.053502082824707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2545.432861328125, "min": 64.47018432617188, "max": 2654.793212890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06941831490428954, "min": 0.06252385611564844, "max": 0.0722157970848653, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27767325961715816, "min": 0.25009542446259375, "max": 0.3610789854243265, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20802730665195224, "min": 0.12012432710331518, "max": 0.30162008124239303, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.832109226607809, "min": 0.4804973084132607, "max": 1.5081004062119652, "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": 25.454545454545453, "min": 3.4545454545454546, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 152.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.4545454545454546, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 152.0, "max": 1415.0, "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": "1791966110", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/mlagents-env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1791966536" }, "total": 425.87156053299987, "count": 1, "self": 0.42992849500001284, "children": { "run_training.setup": { "total": 0.01888879799980714, "count": 1, "self": 0.01888879799980714 }, "TrainerController.start_learning": { "total": 425.42274324000005, "count": 1, "self": 0.3758005559952835, "children": { "TrainerController._reset_env": { "total": 2.9234073140000874, "count": 1, "self": 2.9234073140000874 }, "TrainerController.advance": { "total": 422.04483348700455, "count": 18192, "self": 0.3906992460292713, "children": { "env_step": { "total": 309.5986912669889, "count": 18192, "self": 240.05448786501734, "children": { "SubprocessEnvManager._take_step": { "total": 69.3204231239929, "count": 18192, "self": 1.241812373001494, "children": { "TorchPolicy.evaluate": { "total": 68.0786107509914, "count": 18192, "self": 68.0786107509914 } } }, "workers": { "total": 0.22378027797867617, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 424.30657225599, "count": 18192, "is_parallel": true, "self": 213.2501154609929, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005508526999847163, "count": 1, "is_parallel": true, "self": 0.0041569349996279925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013515920002191706, "count": 10, "is_parallel": true, "self": 0.0013515920002191706 } } }, "UnityEnvironment.step": { "total": 0.03695747999995547, "count": 1, "is_parallel": true, "self": 0.000545560000318801, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003967289999309287, "count": 1, "is_parallel": true, "self": 0.0003967289999309287 }, "communicator.exchange": { "total": 0.03397162099986417, "count": 1, "is_parallel": true, "self": 0.03397162099986417 }, "steps_from_proto": { "total": 0.0020435699998415657, "count": 1, "is_parallel": true, "self": 0.00039050700002007943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016530629998214863, "count": 10, "is_parallel": true, "self": 0.0016530629998214863 } } } } } } }, "UnityEnvironment.step": { "total": 211.05645679499708, "count": 18191, "is_parallel": true, "self": 10.40872872999239, "children": { "UnityEnvironment._generate_step_input": { "total": 5.523740569980191, "count": 18191, "is_parallel": true, "self": 5.523740569980191 }, "communicator.exchange": { "total": 160.39830230899884, "count": 18191, "is_parallel": true, "self": 160.39830230899884 }, "steps_from_proto": { "total": 34.72568518602566, "count": 18191, "is_parallel": true, "self": 6.224981171970967, "children": { "_process_rank_one_or_two_observation": { "total": 28.50070401405469, "count": 181910, "is_parallel": true, "self": 28.50070401405469 } } } } } } } } } } }, "trainer_advance": { "total": 112.05544297398637, "count": 18192, "self": 0.44970744899183046, "children": { "process_trajectory": { "total": 23.661262963994204, "count": 18192, "self": 23.26779559499414, "children": { "RLTrainer._checkpoint": { "total": 0.3934673690000636, "count": 4, "self": 0.3934673690000636 } } }, "_update_policy": { "total": 87.94447256100034, "count": 90, "self": 35.13012057299511, "children": { "TorchPPOOptimizer.update": { "total": 52.81435198800523, "count": 4587, "self": 52.81435198800523 } } } } } } }, "trainer_threads": { "total": 1.1500001164677087e-06, "count": 1, "self": 1.1500001164677087e-06 }, "TrainerController._save_models": { "total": 0.07870073300000513, "count": 1, "self": 0.0007770959996378224, "children": { "RLTrainer._checkpoint": { "total": 0.07792363700036731, "count": 1, "self": 0.07792363700036731 } } } } } } }