{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.90290367603302, "min": 0.90290367603302, "max": 2.857667922973633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8581.1962890625, "min": 8581.1962890625, "max": 29171.07421875, "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": 12.922199249267578, "min": 0.547727644443512, "max": 12.922199249267578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.828857421875, "min": 106.25916290283203, "max": 2615.2138671875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07383112957491084, "min": 0.06289154015710878, "max": 0.07383112957491084, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29532451829964335, "min": 0.2566959803818962, "max": 0.3559083703630855, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18360737736756896, "min": 0.12361180260503554, "max": 0.28361692697394125, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7344295094702759, "min": 0.49444721042014217, "max": 1.4180846348697063, "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": 25.59090909090909, "min": 3.75, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 165.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.75, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 165.0, "max": 1403.0, "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": "1775640671", "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": "1775641186" }, "total": 515.7371517879999, "count": 1, "self": 0.5355481149997559, "children": { "run_training.setup": { "total": 0.029894897000076526, "count": 1, "self": 0.029894897000076526 }, "TrainerController.start_learning": { "total": 515.1717087760001, "count": 1, "self": 0.44976438900891935, "children": { "TrainerController._reset_env": { "total": 3.613090886000009, "count": 1, "self": 3.613090886000009 }, "TrainerController.advance": { "total": 511.0178313079913, "count": 18192, "self": 0.46766963300547104, "children": { "env_step": { "total": 378.3834207429894, "count": 18192, "self": 296.059643676016, "children": { "SubprocessEnvManager._take_step": { "total": 82.05908661199226, "count": 18192, "self": 1.467702041984353, "children": { "TorchPolicy.evaluate": { "total": 80.5913845700079, "count": 18192, "self": 80.5913845700079 } } }, "workers": { "total": 0.26469045498117794, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 512.8380234650117, "count": 18192, "is_parallel": true, "self": 252.93570228799922, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005434188999970502, "count": 1, "is_parallel": true, "self": 0.00383702500016625, "children": { "_process_rank_one_or_two_observation": { "total": 0.001597163999804252, "count": 10, "is_parallel": true, "self": 0.001597163999804252 } } }, "UnityEnvironment.step": { "total": 0.07691397600001437, "count": 1, "is_parallel": true, "self": 0.0007252190000599512, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000451492999900438, "count": 1, "is_parallel": true, "self": 0.000451492999900438 }, "communicator.exchange": { "total": 0.07147464199999831, "count": 1, "is_parallel": true, "self": 0.07147464199999831 }, "steps_from_proto": { "total": 0.004262622000055671, "count": 1, "is_parallel": true, "self": 0.00040748800006440433, "children": { "_process_rank_one_or_two_observation": { "total": 0.003855133999991267, "count": 10, "is_parallel": true, "self": 0.003855133999991267 } } } } } } }, "UnityEnvironment.step": { "total": 259.9023211770125, "count": 18191, "is_parallel": true, "self": 11.954734494993772, "children": { "UnityEnvironment._generate_step_input": { "total": 6.377827879995721, "count": 18191, "is_parallel": true, "self": 6.377827879995721 }, "communicator.exchange": { "total": 197.68831062700212, "count": 18191, "is_parallel": true, "self": 197.68831062700212 }, "steps_from_proto": { "total": 43.881448175020864, "count": 18191, "is_parallel": true, "self": 7.537716884013776, "children": { "_process_rank_one_or_two_observation": { "total": 36.34373129100709, "count": 181910, "is_parallel": true, "self": 36.34373129100709 } } } } } } } } } } }, "trainer_advance": { "total": 132.1667409319964, "count": 18192, "self": 0.535443234009449, "children": { "process_trajectory": { "total": 30.300311558988028, "count": 18192, "self": 29.81309932898796, "children": { "RLTrainer._checkpoint": { "total": 0.4872122300000683, "count": 4, "self": 0.4872122300000683 } } }, "_update_policy": { "total": 101.33098613899892, "count": 90, "self": 41.323106336001615, "children": { "TorchPPOOptimizer.update": { "total": 60.00787980299731, "count": 4587, "self": 60.00787980299731 } } } } } } }, "trainer_threads": { "total": 1.4509998891298892e-06, "count": 1, "self": 1.4509998891298892e-06 }, "TrainerController._save_models": { "total": 0.09102074199995513, "count": 1, "self": 0.0010112990000834543, "children": { "RLTrainer._checkpoint": { "total": 0.09000944299987168, "count": 1, "self": 0.09000944299987168 } } } } } } }