{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.127758264541626, "min": 1.127758264541626, "max": 2.8530564308166504, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10817.45703125, "min": 10817.45703125, "max": 29343.685546875, "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": 13.342976570129395, "min": 0.42259612679481506, "max": 13.342976570129395, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2601.88037109375, "min": 81.98365020751953, "max": 2732.46337890625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06675720262151742, "min": 0.06254128525184818, "max": 0.07492010378118245, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2670288104860697, "min": 0.25923942435788466, "max": 0.3672333581498071, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20792854131728997, "min": 0.14113803842451936, "max": 0.3251086139649737, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8317141652691599, "min": 0.5645521536980774, "max": 1.391468170318095, "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": 26.045454545454547, "min": 3.840909090909091, "max": 26.381818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 169.0, "max": 1451.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 3.840909090909091, "max": 26.381818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 169.0, "max": 1451.0, "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": "1704660107", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTargetNorm --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1704660577" }, "total": 470.01215595999975, "count": 1, "self": 0.43350531499982026, "children": { "run_training.setup": { "total": 0.04527551299997867, "count": 1, "self": 0.04527551299997867 }, "TrainerController.start_learning": { "total": 469.53337513199995, "count": 1, "self": 0.5289272990198697, "children": { "TrainerController._reset_env": { "total": 1.8444162490000053, "count": 1, "self": 1.8444162490000053 }, "TrainerController.advance": { "total": 467.0387818119798, "count": 18205, "self": 0.2606715079609785, "children": { "env_step": { "total": 466.7781103040188, "count": 18205, "self": 298.0949224399783, "children": { "SubprocessEnvManager._take_step": { "total": 168.3995507679847, "count": 18205, "self": 1.5081894449931497, "children": { "TorchPolicy.evaluate": { "total": 166.89136132299154, "count": 18205, "self": 166.89136132299154 } } }, "workers": { "total": 0.283637096055827, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 468.2429345689852, "count": 18205, "is_parallel": true, "self": 244.73288004601045, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002579008999873622, "count": 1, "is_parallel": true, "self": 0.0007307010009753867, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018483079988982354, "count": 10, "is_parallel": true, "self": 0.0018483079988982354 } } }, "UnityEnvironment.step": { "total": 0.03680281000015384, "count": 1, "is_parallel": true, "self": 0.000644504000320012, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043893499969271943, "count": 1, "is_parallel": true, "self": 0.00043893499969271943 }, "communicator.exchange": { "total": 0.03350800899988826, "count": 1, "is_parallel": true, "self": 0.03350800899988826 }, "steps_from_proto": { "total": 0.002211362000252848, "count": 1, "is_parallel": true, "self": 0.0003915690012945561, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018197929989582917, "count": 10, "is_parallel": true, "self": 0.0018197929989582917 } } } } } } }, "UnityEnvironment.step": { "total": 223.51005452297477, "count": 18204, "is_parallel": true, "self": 10.437711326947465, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1885859980120586, "count": 18204, "is_parallel": true, "self": 5.1885859980120586 }, "communicator.exchange": { "total": 171.53052284798878, "count": 18204, "is_parallel": true, "self": 171.53052284798878 }, "steps_from_proto": { "total": 36.35323435002647, "count": 18204, "is_parallel": true, "self": 6.579203484086975, "children": { "_process_rank_one_or_two_observation": { "total": 29.774030865939494, "count": 182040, "is_parallel": true, "self": 29.774030865939494 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001214310000250407, "count": 1, "self": 0.0001214310000250407, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.94796281602976, "count": 621226, "is_parallel": true, "self": 12.779857648179586, "children": { "process_trajectory": { "total": 261.2980096818501, "count": 621226, "is_parallel": true, "self": 260.4070634278505, "children": { "RLTrainer._checkpoint": { "total": 0.890946253999573, "count": 4, "is_parallel": true, "self": 0.890946253999573 } } }, "_update_policy": { "total": 187.87009548600008, "count": 90, "is_parallel": true, "self": 67.42968477998602, "children": { "TorchPPOOptimizer.update": { "total": 120.44041070601406, "count": 4587, "is_parallel": true, "self": 120.44041070601406 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12112834100025793, "count": 1, "self": 0.0012934460000906256, "children": { "RLTrainer._checkpoint": { "total": 0.11983489500016731, "count": 1, "self": 0.11983489500016731 } } } } } } }