{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9620283246040344, "min": 0.9620283246040344, "max": 2.867304563522339, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9143.1171875, "min": 9143.1171875, "max": 29269.4453125, "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": 13.138323783874512, "min": 0.25758981704711914, "max": 13.138323783874512, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2561.97314453125, "min": 49.97242736816406, "max": 2669.353515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06012399918536711, "min": 0.06012399918536711, "max": 0.07639028564752902, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24049599674146843, "min": 0.24049599674146843, "max": 0.36016795410393443, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19520237910396912, "min": 0.13120590685067846, "max": 0.29419944841487733, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7808095164158765, "min": 0.5248236274027138, "max": 1.4709972420743866, "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": 25.886363636363637, "min": 3.590909090909091, "max": 26.01818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 158.0, "max": 1431.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.590909090909091, "max": 26.01818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 158.0, "max": 1431.0, "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": "1774516993", "python_version": "3.10.12 (main, Mar 26 2026, 08:57:09) [GCC 11.4.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1774517652" }, "total": 658.9953637879998, "count": 1, "self": 0.5389557970001988, "children": { "run_training.setup": { "total": 0.027067356999850745, "count": 1, "self": 0.027067356999850745 }, "TrainerController.start_learning": { "total": 658.4293406339998, "count": 1, "self": 0.6504912779387269, "children": { "TrainerController._reset_env": { "total": 2.505038341999807, "count": 1, "self": 2.505038341999807 }, "TrainerController.advance": { "total": 655.1626470660617, "count": 18192, "self": 0.6973801380472651, "children": { "env_step": { "total": 474.3225228539809, "count": 18192, "self": 367.14831215703, "children": { "SubprocessEnvManager._take_step": { "total": 106.77208549002307, "count": 18192, "self": 2.0967400040494795, "children": { "TorchPolicy.evaluate": { "total": 104.6753454859736, "count": 18192, "self": 104.6753454859736 } } }, "workers": { "total": 0.4021252069278489, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 655.2187336440315, "count": 18192, "is_parallel": true, "self": 339.599060131035, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002587308000329358, "count": 1, "is_parallel": true, "self": 0.0007766989997435303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018106090005858277, "count": 10, "is_parallel": true, "self": 0.0018106090005858277 } } }, "UnityEnvironment.step": { "total": 0.042542885999864666, "count": 1, "is_parallel": true, "self": 0.0006956380002520746, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005574859997068415, "count": 1, "is_parallel": true, "self": 0.0005574859997068415 }, "communicator.exchange": { "total": 0.03868434799960596, "count": 1, "is_parallel": true, "self": 0.03868434799960596 }, "steps_from_proto": { "total": 0.0026054140002997883, "count": 1, "is_parallel": true, "self": 0.0005307650003487652, "children": { "_process_rank_one_or_two_observation": { "total": 0.002074648999951023, "count": 10, "is_parallel": true, "self": 0.002074648999951023 } } } } } } }, "UnityEnvironment.step": { "total": 315.61967351299654, "count": 18191, "is_parallel": true, "self": 14.092061497235136, "children": { "UnityEnvironment._generate_step_input": { "total": 8.780506324909311, "count": 18191, "is_parallel": true, "self": 8.780506324909311 }, "communicator.exchange": { "total": 235.25572917790169, "count": 18191, "is_parallel": true, "self": 235.25572917790169 }, "steps_from_proto": { "total": 57.49137651295041, "count": 18191, "is_parallel": true, "self": 10.688042399899132, "children": { "_process_rank_one_or_two_observation": { "total": 46.80333411305128, "count": 181910, "is_parallel": true, "self": 46.80333411305128 } } } } } } } } } } }, "trainer_advance": { "total": 180.14274407403354, "count": 18192, "self": 0.8370863640507196, "children": { "process_trajectory": { "total": 40.909788694981216, "count": 18192, "self": 40.39082906698059, "children": { "RLTrainer._checkpoint": { "total": 0.5189596280006299, "count": 4, "self": 0.5189596280006299 } } }, "_update_policy": { "total": 138.3958690150016, "count": 90, "self": 66.3936062779585, "children": { "TorchPPOOptimizer.update": { "total": 72.00226273704311, "count": 4587, "self": 72.00226273704311 } } } } } } }, "trainer_threads": { "total": 1.3170001693652011e-06, "count": 1, "self": 1.3170001693652011e-06 }, "TrainerController._save_models": { "total": 0.11116263099938806, "count": 1, "self": 0.0012555889989016578, "children": { "RLTrainer._checkpoint": { "total": 0.1099070420004864, "count": 1, "self": 0.1099070420004864 } } } } } } }