{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0279631614685059, "min": 1.0279631614685059, "max": 2.867321252822876, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9826.2998046875, "min": 9826.2998046875, "max": 29395.77734375, "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": 11.7504243850708, "min": 0.2524029016494751, "max": 11.7504243850708, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2291.332763671875, "min": 48.966163635253906, "max": 2352.94287109375, "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": 0.0709494298588848, "min": 0.06142763798138107, "max": 0.07520414394584449, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2837977194355392, "min": 0.24571055192552427, "max": 0.3760207197292224, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20475001932651388, "min": 0.1187521502393864, "max": 0.26916437856122555, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8190000773060555, "min": 0.4750086009575456, "max": 1.3458218928061279, "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": 24.045454545454547, "min": 3.25, "max": 24.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1058.0, "min": 143.0, "max": 1266.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.045454545454547, "min": 3.25, "max": 24.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1058.0, "min": 143.0, "max": 1266.0, "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": "1717827566", "python_version": "3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]", "command_line_arguments": "/home/raghu/anaconda3/envs/rl/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717827732" }, "total": 166.1779586749999, "count": 1, "self": 0.16811870299898146, "children": { "run_training.setup": { "total": 0.012018883000564529, "count": 1, "self": 0.012018883000564529 }, "TrainerController.start_learning": { "total": 165.99782108900035, "count": 1, "self": 0.2624971379991621, "children": { "TrainerController._reset_env": { "total": 1.2432652869993035, "count": 1, "self": 1.2432652869993035 }, "TrainerController.advance": { "total": 164.44931308900232, "count": 18203, "self": 0.10917209904346237, "children": { "env_step": { "total": 164.34014098995885, "count": 18203, "self": 116.99113025104634, "children": { "SubprocessEnvManager._take_step": { "total": 47.221452809904804, "count": 18203, "self": 0.532330039018234, "children": { "TorchPolicy.evaluate": { "total": 46.68912277088657, "count": 18203, "self": 46.68912277088657 } } }, "workers": { "total": 0.12755792900770757, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 165.70048179094556, "count": 18203, "is_parallel": true, "self": 80.56517391897523, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001716224000119837, "count": 1, "is_parallel": true, "self": 0.0010312680005881703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006849559995316667, "count": 10, "is_parallel": true, "self": 0.0006849559995316667 } } }, "UnityEnvironment.step": { "total": 0.0126091929996619, "count": 1, "is_parallel": true, "self": 0.0001914710010169074, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019679899924085476, "count": 1, "is_parallel": true, "self": 0.00019679899924085476 }, "communicator.exchange": { "total": 0.011707337999723677, "count": 1, "is_parallel": true, "self": 0.011707337999723677 }, "steps_from_proto": { "total": 0.0005135849996804609, "count": 1, "is_parallel": true, "self": 0.00011790200096584158, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003956829987146193, "count": 10, "is_parallel": true, "self": 0.0003956829987146193 } } } } } } }, "UnityEnvironment.step": { "total": 85.13530787197033, "count": 18202, "is_parallel": true, "self": 3.840323996085317, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6529291919132447, "count": 18202, "is_parallel": true, "self": 2.6529291919132447 }, "communicator.exchange": { "total": 67.41352413199638, "count": 18202, "is_parallel": true, "self": 67.41352413199638 }, "steps_from_proto": { "total": 11.228530551975382, "count": 18202, "is_parallel": true, "self": 2.0383672699608724, "children": { "_process_rank_one_or_two_observation": { "total": 9.19016328201451, "count": 182020, "is_parallel": true, "self": 9.19016328201451 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013606599986815127, "count": 1, "self": 0.00013606599986815127, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 164.11276653164896, "count": 185808, "is_parallel": true, "self": 1.3819273636800062, "children": { "process_trajectory": { "total": 90.07494031897022, "count": 185808, "is_parallel": true, "self": 89.72843368097074, "children": { "RLTrainer._checkpoint": { "total": 0.34650663799948234, "count": 4, "is_parallel": true, "self": 0.34650663799948234 } } }, "_update_policy": { "total": 72.65589884899873, "count": 90, "is_parallel": true, "self": 16.892796432961404, "children": { "TorchPPOOptimizer.update": { "total": 55.76310241603733, "count": 4587, "is_parallel": true, "self": 55.76310241603733 } } } } } } } } }, "TrainerController._save_models": { "total": 0.042609508999703394, "count": 1, "self": 0.0009175530003631138, "children": { "RLTrainer._checkpoint": { "total": 0.04169195599934028, "count": 1, "self": 0.04169195599934028 } } } } } } }