{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8482237458229065, "min": 0.8482237458229065, "max": 2.84915828704834, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8061.5185546875, "min": 8061.5185546875, "max": 29084.20703125, "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": 13.095726013183594, "min": 0.4086481034755707, "max": 13.124811172485352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2553.66650390625, "min": 79.2777328491211, "max": 2677.46142578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06564096225124291, "min": 0.06129962359520826, "max": 0.07477135371585722, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26256384900497165, "min": 0.2472820886691539, "max": 0.36302068916277264, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18541013705087644, "min": 0.12491344134140686, "max": 0.30576618797346655, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7416405482035058, "min": 0.49965376536562744, "max": 1.4710161364546008, "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": 25.545454545454547, "min": 3.7045454545454546, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1124.0, "min": 163.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.545454545454547, "min": 3.7045454545454546, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1124.0, "min": 163.0, "max": 1407.0, "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": "1728370875", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728371310" }, "total": 434.53301765000015, "count": 1, "self": 0.4291555050001534, "children": { "run_training.setup": { "total": 0.06247789600001852, "count": 1, "self": 0.06247789600001852 }, "TrainerController.start_learning": { "total": 434.041384249, "count": 1, "self": 0.35184103800656885, "children": { "TrainerController._reset_env": { "total": 1.6660250580000593, "count": 1, "self": 1.6660250580000593 }, "TrainerController.advance": { "total": 431.93481309899335, "count": 18192, "self": 0.3819242199920154, "children": { "env_step": { "total": 305.53506225899696, "count": 18192, "self": 231.2297604520054, "children": { "SubprocessEnvManager._take_step": { "total": 74.09445791498183, "count": 18192, "self": 1.2544560029928107, "children": { "TorchPolicy.evaluate": { "total": 72.84000191198902, "count": 18192, "self": 72.84000191198902 } } }, "workers": { "total": 0.2108438920097342, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 432.6587929119962, "count": 18192, "is_parallel": true, "self": 230.3419365029779, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002354165000042485, "count": 1, "is_parallel": true, "self": 0.0007601169997997204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015940480002427648, "count": 10, "is_parallel": true, "self": 0.0015940480002427648 } } }, "UnityEnvironment.step": { "total": 0.03726316200004476, "count": 1, "is_parallel": true, "self": 0.0007553410000582517, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003786219999710738, "count": 1, "is_parallel": true, "self": 0.0003786219999710738 }, "communicator.exchange": { "total": 0.03413820199989459, "count": 1, "is_parallel": true, "self": 0.03413820199989459 }, "steps_from_proto": { "total": 0.001990997000120842, "count": 1, "is_parallel": true, "self": 0.0003795520001403929, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016114449999804492, "count": 10, "is_parallel": true, "self": 0.0016114449999804492 } } } } } } }, "UnityEnvironment.step": { "total": 202.31685640901833, "count": 18191, "is_parallel": true, "self": 10.000972774989577, "children": { "UnityEnvironment._generate_step_input": { "total": 5.233685026019884, "count": 18191, "is_parallel": true, "self": 5.233685026019884 }, "communicator.exchange": { "total": 155.44807276299866, "count": 18191, "is_parallel": true, "self": 155.44807276299866 }, "steps_from_proto": { "total": 31.634125845010203, "count": 18191, "is_parallel": true, "self": 5.729833816972814, "children": { "_process_rank_one_or_two_observation": { "total": 25.90429202803739, "count": 181910, "is_parallel": true, "self": 25.90429202803739 } } } } } } } } } } }, "trainer_advance": { "total": 126.01782662000437, "count": 18192, "self": 0.4167006720279005, "children": { "process_trajectory": { "total": 27.509874090977064, "count": 18192, "self": 27.04743004497709, "children": { "RLTrainer._checkpoint": { "total": 0.46244404599997324, "count": 4, "self": 0.46244404599997324 } } }, "_update_policy": { "total": 98.0912518569994, "count": 90, "self": 41.34862859799409, "children": { "TorchPPOOptimizer.update": { "total": 56.74262325900531, "count": 4587, "self": 56.74262325900531 } } } } } } }, "trainer_threads": { "total": 9.289999525208259e-07, "count": 1, "self": 9.289999525208259e-07 }, "TrainerController._save_models": { "total": 0.08870412500004932, "count": 1, "self": 0.0009131279998655373, "children": { "RLTrainer._checkpoint": { "total": 0.08779099700018378, "count": 1, "self": 0.08779099700018378 } } } } } } }