{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.984443724155426, "min": 0.984443724155426, "max": 2.864163637161255, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9486.099609375, "min": 9486.099609375, "max": 29363.40625, "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": 12.900522232055664, "min": 0.35167303681373596, "max": 12.959044456481934, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.601806640625, "min": 68.22457122802734, "max": 2643.64501953125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06518149384247213, "min": 0.06222869860311951, "max": 0.0752718205850197, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2607259753698885, "min": 0.2567263780054454, "max": 0.3750874952774942, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20359636616765284, "min": 0.12076589190081566, "max": 0.2847806413968404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8143854646706113, "min": 0.48306356760326263, "max": 1.423903206984202, "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.CumulativeReward.mean": { "value": 24.863636363636363, "min": 3.5, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1094.0, "min": 154.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.863636363636363, "min": 3.5, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1094.0, "min": 154.0, "max": 1416.0, "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": "1728213167", "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=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728213814" }, "total": 646.8791222320001, "count": 1, "self": 0.593731211999966, "children": { "run_training.setup": { "total": 0.09422809100010454, "count": 1, "self": 0.09422809100010454 }, "TrainerController.start_learning": { "total": 646.191162929, "count": 1, "self": 0.9496246359908582, "children": { "TrainerController._reset_env": { "total": 3.9496398409999074, "count": 1, "self": 3.9496398409999074 }, "TrainerController.advance": { "total": 641.1966530510094, "count": 18210, "self": 0.490651512991235, "children": { "env_step": { "total": 640.7060015380182, "count": 18210, "self": 486.27789591400733, "children": { "SubprocessEnvManager._take_step": { "total": 153.9684296010073, "count": 18210, "self": 2.9018159180263865, "children": { "TorchPolicy.evaluate": { "total": 151.06661368298091, "count": 18210, "self": 151.06661368298091 } } }, "workers": { "total": 0.459676023003567, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 644.0215044529848, "count": 18210, "is_parallel": true, "self": 313.86576470996465, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055234189999282535, "count": 1, "is_parallel": true, "self": 0.0016805299999305134, "children": { "_process_rank_one_or_two_observation": { "total": 0.00384288899999774, "count": 10, "is_parallel": true, "self": 0.00384288899999774 } } }, "UnityEnvironment.step": { "total": 0.15824653000004218, "count": 1, "is_parallel": true, "self": 0.0012999769999169075, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009505160001026525, "count": 1, "is_parallel": true, "self": 0.0009505160001026525 }, "communicator.exchange": { "total": 0.14419322699995973, "count": 1, "is_parallel": true, "self": 0.14419322699995973 }, "steps_from_proto": { "total": 0.011802810000062891, "count": 1, "is_parallel": true, "self": 0.0006830150002770097, "children": { "_process_rank_one_or_two_observation": { "total": 0.011119794999785881, "count": 10, "is_parallel": true, "self": 0.011119794999785881 } } } } } } }, "UnityEnvironment.step": { "total": 330.15573974302015, "count": 18209, "is_parallel": true, "self": 15.778584725038854, "children": { "UnityEnvironment._generate_step_input": { "total": 7.72115982598757, "count": 18209, "is_parallel": true, "self": 7.72115982598757 }, "communicator.exchange": { "total": 260.35629035399984, "count": 18209, "is_parallel": true, "self": 260.35629035399984 }, "steps_from_proto": { "total": 46.299704837993886, "count": 18209, "is_parallel": true, "self": 9.36548740796502, "children": { "_process_rank_one_or_two_observation": { "total": 36.934217430028866, "count": 182090, "is_parallel": true, "self": 36.934217430028866 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016433500013590674, "count": 1, "self": 0.00016433500013590674, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 633.8699032998413, "count": 732235, "is_parallel": true, "self": 19.43860116795304, "children": { "process_trajectory": { "total": 343.9320606998883, "count": 732235, "is_parallel": true, "self": 343.1372579128881, "children": { "RLTrainer._checkpoint": { "total": 0.7948027870002079, "count": 4, "is_parallel": true, "self": 0.7948027870002079 } } }, "_update_policy": { "total": 270.49924143199996, "count": 90, "is_parallel": true, "self": 71.23474034200035, "children": { "TorchPPOOptimizer.update": { "total": 199.2645010899996, "count": 4587, "is_parallel": true, "self": 199.2645010899996 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09508106599969324, "count": 1, "self": 0.0013119979998919007, "children": { "RLTrainer._checkpoint": { "total": 0.09376906799980134, "count": 1, "self": 0.09376906799980134 } } } } } } }