{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1599631309509277, "min": 1.1599631309509277, "max": 2.860225200653076, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11024.2890625, "min": 11024.2890625, "max": 29197.1796875, "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": 11.5546236038208, "min": 0.07761342823505402, "max": 11.5546236038208, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2253.151611328125, "min": 15.057004928588867, "max": 2332.06005859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06630420807086207, "min": 0.06273398909040992, "max": 0.07721948328224815, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2652168322834483, "min": 0.2533240075047383, "max": 0.35996750798435906, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20018718946798175, "min": 0.10400999385941152, "max": 0.2766077917580511, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.800748757871927, "min": 0.4160399754376461, "max": 1.3830389587902556, "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": 22.954545454545453, "min": 3.1818181818181817, "max": 22.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1010.0, "min": 140.0, "max": 1240.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.954545454545453, "min": 3.1818181818181817, "max": 22.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1010.0, "min": 140.0, "max": 1240.0, "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": "1784485498", "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": "1784485979" }, "total": 480.538542343, "count": 1, "self": 0.4344297839998035, "children": { "run_training.setup": { "total": 0.0257586950001496, "count": 1, "self": 0.0257586950001496 }, "TrainerController.start_learning": { "total": 480.07835386400006, "count": 1, "self": 0.39764779001120587, "children": { "TrainerController._reset_env": { "total": 2.935842907999813, "count": 1, "self": 2.935842907999813 }, "TrainerController.advance": { "total": 476.6596406939891, "count": 18192, "self": 0.4282728899979702, "children": { "env_step": { "total": 352.94438684198917, "count": 18192, "self": 277.8562444859956, "children": { "SubprocessEnvManager._take_step": { "total": 74.84202049400642, "count": 18192, "self": 1.3641526840142433, "children": { "TorchPolicy.evaluate": { "total": 73.47786780999218, "count": 18192, "self": 73.47786780999218 } } }, "workers": { "total": 0.2461218619871488, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 478.21020378301273, "count": 18192, "is_parallel": true, "self": 233.93876674900594, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005011275000015303, "count": 1, "is_parallel": true, "self": 0.0035866459995759215, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014246290004393813, "count": 10, "is_parallel": true, "self": 0.0014246290004393813 } } }, "UnityEnvironment.step": { "total": 0.04273416899991389, "count": 1, "is_parallel": true, "self": 0.0006511889998819242, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004974420000962709, "count": 1, "is_parallel": true, "self": 0.0004974420000962709 }, "communicator.exchange": { "total": 0.039508690000047864, "count": 1, "is_parallel": true, "self": 0.039508690000047864 }, "steps_from_proto": { "total": 0.002076847999887832, "count": 1, "is_parallel": true, "self": 0.0003851480000776064, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016916999998102256, "count": 10, "is_parallel": true, "self": 0.0016916999998102256 } } } } } } }, "UnityEnvironment.step": { "total": 244.2714370340068, "count": 18191, "is_parallel": true, "self": 10.91739171001791, "children": { "UnityEnvironment._generate_step_input": { "total": 5.852628195003263, "count": 18191, "is_parallel": true, "self": 5.852628195003263 }, "communicator.exchange": { "total": 187.2934387729863, "count": 18191, "is_parallel": true, "self": 187.2934387729863 }, "steps_from_proto": { "total": 40.20797835599933, "count": 18191, "is_parallel": true, "self": 7.156564671008937, "children": { "_process_rank_one_or_two_observation": { "total": 33.05141368499039, "count": 181910, "is_parallel": true, "self": 33.05141368499039 } } } } } } } } } } }, "trainer_advance": { "total": 123.28698096200196, "count": 18192, "self": 0.521894577023204, "children": { "process_trajectory": { "total": 25.486871345979353, "count": 18192, "self": 25.08190940597933, "children": { "RLTrainer._checkpoint": { "total": 0.40496194000002106, "count": 4, "self": 0.40496194000002106 } } }, "_update_policy": { "total": 97.2782150389994, "count": 90, "self": 40.020215493004116, "children": { "TorchPPOOptimizer.update": { "total": 57.25799954599529, "count": 4587, "self": 57.25799954599529 } } } } } } }, "trainer_threads": { "total": 8.78000037118909e-07, "count": 1, "self": 8.78000037118909e-07 }, "TrainerController._save_models": { "total": 0.08522159399990414, "count": 1, "self": 0.0007465959999990446, "children": { "RLTrainer._checkpoint": { "total": 0.0844749979999051, "count": 1, "self": 0.0844749979999051 } } } } } } }