{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9110981822013855, "min": 0.9110981822013855, "max": 2.8659684658050537, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8709.1875, "min": 8709.1875, "max": 29350.3828125, "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": 12.819787979125977, "min": 0.3606634736061096, "max": 12.819787979125977, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.858642578125, "min": 69.96871185302734, "max": 2599.626220703125, "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.Losses.PolicyLoss.mean": { "value": 0.07406934831969386, "min": 0.06275595650075438, "max": 0.07696478446573476, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29627739327877545, "min": 0.25102382600301754, "max": 0.3848239223286738, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19320569048617398, "min": 0.10319211429290875, "max": 0.2857423303758397, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7728227619446959, "min": 0.412768457171635, "max": 1.4287116518791985, "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": 25.363636363636363, "min": 2.8863636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 127.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 2.8863636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 127.0, "max": 1392.0, "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": "1700665854", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700666347" }, "total": 492.794877114, "count": 1, "self": 0.4255169360000082, "children": { "run_training.setup": { "total": 0.0647999110000228, "count": 1, "self": 0.0647999110000228 }, "TrainerController.start_learning": { "total": 492.30456026699994, "count": 1, "self": 0.5845600950052017, "children": { "TrainerController._reset_env": { "total": 9.359620545000041, "count": 1, "self": 9.359620545000041 }, "TrainerController.advance": { "total": 482.27274705099467, "count": 18200, "self": 0.2755327279981543, "children": { "env_step": { "total": 481.9972143229965, "count": 18200, "self": 332.68452949099026, "children": { "SubprocessEnvManager._take_step": { "total": 149.0248275340046, "count": 18200, "self": 1.5094469430013646, "children": { "TorchPolicy.evaluate": { "total": 147.51538059100324, "count": 18200, "self": 147.51538059100324 } } }, "workers": { "total": 0.28785729800165427, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 491.0147283569916, "count": 18200, "is_parallel": true, "self": 242.13867466298603, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006084477000001698, "count": 1, "is_parallel": true, "self": 0.0039771109998696375, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021073660001320604, "count": 10, "is_parallel": true, "self": 0.0021073660001320604 } } }, "UnityEnvironment.step": { "total": 0.055176678999998785, "count": 1, "is_parallel": true, "self": 0.0007027749999792832, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005000200000040422, "count": 1, "is_parallel": true, "self": 0.0005000200000040422 }, "communicator.exchange": { "total": 0.05158853000000363, "count": 1, "is_parallel": true, "self": 0.05158853000000363 }, "steps_from_proto": { "total": 0.00238535400001183, "count": 1, "is_parallel": true, "self": 0.0005782459999750245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018071080000368056, "count": 10, "is_parallel": true, "self": 0.0018071080000368056 } } } } } } }, "UnityEnvironment.step": { "total": 248.87605369400558, "count": 18199, "is_parallel": true, "self": 10.847131040000704, "children": { "UnityEnvironment._generate_step_input": { "total": 5.600561382003264, "count": 18199, "is_parallel": true, "self": 5.600561382003264 }, "communicator.exchange": { "total": 196.40041242400758, "count": 18199, "is_parallel": true, "self": 196.40041242400758 }, "steps_from_proto": { "total": 36.027948847994026, "count": 18199, "is_parallel": true, "self": 6.922526336994849, "children": { "_process_rank_one_or_two_observation": { "total": 29.105422510999176, "count": 181990, "is_parallel": true, "self": 29.105422510999176 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.638400005456788e-05, "count": 1, "self": 3.638400005456788e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 478.0624262400035, "count": 497806, "is_parallel": true, "self": 10.887787223969667, "children": { "process_trajectory": { "total": 271.35833625103413, "count": 497806, "is_parallel": true, "self": 270.5450503750341, "children": { "RLTrainer._checkpoint": { "total": 0.813285876000009, "count": 4, "is_parallel": true, "self": 0.813285876000009 } } }, "_update_policy": { "total": 195.8163027649997, "count": 90, "is_parallel": true, "self": 63.47548170399756, "children": { "TorchPPOOptimizer.update": { "total": 132.34082106100215, "count": 4587, "is_parallel": true, "self": 132.34082106100215 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08759619199997815, "count": 1, "self": 0.000812365999991016, "children": { "RLTrainer._checkpoint": { "total": 0.08678382599998713, "count": 1, "self": 0.08678382599998713 } } } } } } }