{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7155816555023193, "min": 0.7155816555023193, "max": 2.833850860595703, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6800.88818359375, "min": 6800.88818359375, "max": 28927.94921875, "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": 13.008702278137207, "min": 0.49831342697143555, "max": 13.008702278137207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2536.697021484375, "min": 96.67280578613281, "max": 2653.677734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06954916204039382, "min": 0.062318578521451715, "max": 0.07293804858362658, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2781966481615753, "min": 0.25396745574236024, "max": 0.3646902429181329, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16951767263897494, "min": 0.15422794802739814, "max": 0.29912495510835274, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6780706905558997, "min": 0.6169117921095926, "max": 1.4018813777788013, "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": 25.90909090909091, "min": 4.090909090909091, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 180.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 4.090909090909091, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 180.0, "max": 1412.0, "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": "1756541388", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/project/lt200258-aithai/jack/ml-agents/env/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": "1756541678" }, "total": 289.40144578460604, "count": 1, "self": 1.355534240603447, "children": { "run_training.setup": { "total": 0.1302944077178836, "count": 1, "self": 0.1302944077178836 }, "TrainerController.start_learning": { "total": 287.9156171362847, "count": 1, "self": 0.2209981819614768, "children": { "TrainerController._reset_env": { "total": 23.01650570705533, "count": 1, "self": 23.01650570705533 }, "TrainerController.advance": { "total": 264.6156094064936, "count": 18192, "self": 0.22802122123539448, "children": { "env_step": { "total": 185.7479436462745, "count": 18192, "self": 135.48012878838927, "children": { "SubprocessEnvManager._take_step": { "total": 50.12693567574024, "count": 18192, "self": 0.7754549430683255, "children": { "TorchPolicy.evaluate": { "total": 49.35148073267192, "count": 18192, "self": 49.35148073267192 } } }, "workers": { "total": 0.1408791821449995, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 287.55474940594286, "count": 18192, "is_parallel": true, "self": 167.57470546569675, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.047285452485084534, "count": 1, "is_parallel": true, "self": 0.0009547341614961624, "children": { "_process_rank_one_or_two_observation": { "total": 0.04633071832358837, "count": 10, "is_parallel": true, "self": 0.04633071832358837 } } }, "UnityEnvironment.step": { "total": 0.04602481983602047, "count": 1, "is_parallel": true, "self": 0.00031233206391334534, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002309763804078102, "count": 1, "is_parallel": true, "self": 0.0002309763804078102 }, "communicator.exchange": { "total": 0.044496030546724796, "count": 1, "is_parallel": true, "self": 0.044496030546724796 }, "steps_from_proto": { "total": 0.0009854808449745178, "count": 1, "is_parallel": true, "self": 0.0001954576000571251, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007900232449173927, "count": 10, "is_parallel": true, "self": 0.0007900232449173927 } } } } } } }, "UnityEnvironment.step": { "total": 119.9800439402461, "count": 18191, "is_parallel": true, "self": 4.869261859916151, "children": { "UnityEnvironment._generate_step_input": { "total": 2.757818111218512, "count": 18191, "is_parallel": true, "self": 2.757818111218512 }, "communicator.exchange": { "total": 97.58973650168628, "count": 18191, "is_parallel": true, "self": 97.58973650168628 }, "steps_from_proto": { "total": 14.763227467425168, "count": 18191, "is_parallel": true, "self": 2.6201242972165346, "children": { "_process_rank_one_or_two_observation": { "total": 12.143103170208633, "count": 181910, "is_parallel": true, "self": 12.143103170208633 } } } } } } } } } } }, "trainer_advance": { "total": 78.6396445389837, "count": 18192, "self": 0.23935331031680107, "children": { "process_trajectory": { "total": 18.32188151963055, "count": 18192, "self": 16.91800756379962, "children": { "RLTrainer._checkpoint": { "total": 1.4038739558309317, "count": 4, "self": 1.4038739558309317 } } }, "_update_policy": { "total": 60.07840970903635, "count": 90, "self": 22.647509918548167, "children": { "TorchPPOOptimizer.update": { "total": 37.43089979048818, "count": 4587, "self": 37.43089979048818 } } } } } } }, "trainer_threads": { "total": 9.32253897190094e-07, "count": 1, "self": 9.32253897190094e-07 }, "TrainerController._save_models": { "total": 0.06250290852040052, "count": 1, "self": 0.0027099689468741417, "children": { "RLTrainer._checkpoint": { "total": 0.05979293957352638, "count": 1, "self": 0.05979293957352638 } } } } } } }