{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7969645261764526, "min": 0.7969645261764526, "max": 2.8665213584899902, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7574.3505859375, "min": 7574.3505859375, "max": 29261.451171875, "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": 13.138544082641602, "min": 0.33093196153640747, "max": 13.138544082641602, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2562.01611328125, "min": 64.20079803466797, "max": 2670.848876953125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07246021267012254, "min": 0.05865263021003235, "max": 0.07257303378933369, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28984085068049015, "min": 0.24522058823055765, "max": 0.3628651689466685, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18259700186842798, "min": 0.09417892445686876, "max": 0.2912943778815223, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7303880074737119, "min": 0.37671569782747505, "max": 1.4000544556800056, "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": 25.772727272727273, "min": 2.7954545454545454, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 123.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 2.7954545454545454, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 123.0, "max": 1423.0, "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": "1781624897", "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", "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": "1781625374" }, "total": 477.352408149, "count": 1, "self": 0.4861424820001048, "children": { "run_training.setup": { "total": 0.026486365999971895, "count": 1, "self": 0.026486365999971895 }, "TrainerController.start_learning": { "total": 476.8397793009999, "count": 1, "self": 0.42806884498929776, "children": { "TrainerController._reset_env": { "total": 3.0541364090000798, "count": 1, "self": 3.0541364090000798 }, "TrainerController.advance": { "total": 473.27669358301046, "count": 18192, "self": 0.4426838099868746, "children": { "env_step": { "total": 348.5060623660197, "count": 18192, "self": 272.0215923230278, "children": { "SubprocessEnvManager._take_step": { "total": 76.23901043800345, "count": 18192, "self": 1.3722868999966522, "children": { "TorchPolicy.evaluate": { "total": 74.8667235380068, "count": 18192, "self": 74.8667235380068 } } }, "workers": { "total": 0.24545960498846853, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 475.0836830629986, "count": 18192, "is_parallel": true, "self": 236.55736650498613, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006949884000050588, "count": 1, "is_parallel": true, "self": 0.0045510260000583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023988579999922877, "count": 10, "is_parallel": true, "self": 0.0023988579999922877 } } }, "UnityEnvironment.step": { "total": 0.040142157999980554, "count": 1, "is_parallel": true, "self": 0.0006503439999505645, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005116629999974975, "count": 1, "is_parallel": true, "self": 0.0005116629999974975 }, "communicator.exchange": { "total": 0.03682597199997417, "count": 1, "is_parallel": true, "self": 0.03682597199997417 }, "steps_from_proto": { "total": 0.0021541790000583205, "count": 1, "is_parallel": true, "self": 0.0003942199997482021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017599590003101184, "count": 10, "is_parallel": true, "self": 0.0017599590003101184 } } } } } } }, "UnityEnvironment.step": { "total": 238.52631655801247, "count": 18191, "is_parallel": true, "self": 10.867513992980207, "children": { "UnityEnvironment._generate_step_input": { "total": 6.061012572016239, "count": 18191, "is_parallel": true, "self": 6.061012572016239 }, "communicator.exchange": { "total": 182.289775089994, "count": 18191, "is_parallel": true, "self": 182.289775089994 }, "steps_from_proto": { "total": 39.30801490302201, "count": 18191, "is_parallel": true, "self": 6.940957735993493, "children": { "_process_rank_one_or_two_observation": { "total": 32.36705716702852, "count": 181910, "is_parallel": true, "self": 32.36705716702852 } } } } } } } } } } }, "trainer_advance": { "total": 124.32794740700388, "count": 18192, "self": 0.5053232460064692, "children": { "process_trajectory": { "total": 28.09146490299804, "count": 18192, "self": 27.624970055998006, "children": { "RLTrainer._checkpoint": { "total": 0.4664948470000354, "count": 4, "self": 0.4664948470000354 } } }, "_update_policy": { "total": 95.73115925799937, "count": 90, "self": 38.65660188899551, "children": { "TorchPPOOptimizer.update": { "total": 57.074557369003855, "count": 4587, "self": 57.074557369003855 } } } } } } }, "trainer_threads": { "total": 1.0199998996540671e-06, "count": 1, "self": 1.0199998996540671e-06 }, "TrainerController._save_models": { "total": 0.08087944400017477, "count": 1, "self": 0.000807420000228376, "children": { "RLTrainer._checkpoint": { "total": 0.0800720239999464, "count": 1, "self": 0.0800720239999464 } } } } } } }