{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1188875436782837, "min": 1.1188875436782837, "max": 2.857405185699463, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10670.830078125, "min": 10670.830078125, "max": 29231.25390625, "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": 11.998059272766113, "min": 0.3420446217060089, "max": 11.998059272766113, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2339.62158203125, "min": 66.35665893554688, "max": 2398.4990234375, "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": 0.06351417881395557, "min": 0.06073830023474418, "max": 0.07666239110346627, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2540567152558223, "min": 0.2429532009389767, "max": 0.3574626255870623, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20329319481171812, "min": 0.12440861362333902, "max": 0.2831770246665852, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8131727792468725, "min": 0.4976344544933561, "max": 1.3341458767068153, "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": 3.727272727272727, "max": 24.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1058.0, "min": 164.0, "max": 1304.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.045454545454547, "min": 3.727272727272727, "max": 24.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1058.0, "min": 164.0, "max": 1304.0, "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": "1711104786", "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=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711105237" }, "total": 451.1454547390001, "count": 1, "self": 0.4814510930000324, "children": { "run_training.setup": { "total": 0.053331628000023557, "count": 1, "self": 0.053331628000023557 }, "TrainerController.start_learning": { "total": 450.61067201800006, "count": 1, "self": 0.571187340007782, "children": { "TrainerController._reset_env": { "total": 2.048299474000032, "count": 1, "self": 2.048299474000032 }, "TrainerController.advance": { "total": 447.8976496099924, "count": 18199, "self": 0.2756672879945654, "children": { "env_step": { "total": 447.62198232199785, "count": 18199, "self": 287.9570824020177, "children": { "SubprocessEnvManager._take_step": { "total": 159.37248219599405, "count": 18199, "self": 1.4967882089902105, "children": { "TorchPolicy.evaluate": { "total": 157.87569398700384, "count": 18199, "self": 157.87569398700384 } } }, "workers": { "total": 0.292417723986091, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 449.424849743986, "count": 18199, "is_parallel": true, "self": 223.58693663000304, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002389294999829872, "count": 1, "is_parallel": true, "self": 0.000697024999453788, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016922700003760838, "count": 10, "is_parallel": true, "self": 0.0016922700003760838 } } }, "UnityEnvironment.step": { "total": 0.054872884000133126, "count": 1, "is_parallel": true, "self": 0.0007597340004394937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004187019999335462, "count": 1, "is_parallel": true, "self": 0.0004187019999335462 }, "communicator.exchange": { "total": 0.051583731999926385, "count": 1, "is_parallel": true, "self": 0.051583731999926385 }, "steps_from_proto": { "total": 0.002110715999833701, "count": 1, "is_parallel": true, "self": 0.0004152490000706166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016954669997630845, "count": 10, "is_parallel": true, "self": 0.0016954669997630845 } } } } } } }, "UnityEnvironment.step": { "total": 225.83791311398295, "count": 18198, "is_parallel": true, "self": 10.504462386005343, "children": { "UnityEnvironment._generate_step_input": { "total": 5.542115273991158, "count": 18198, "is_parallel": true, "self": 5.542115273991158 }, "communicator.exchange": { "total": 175.50546024300752, "count": 18198, "is_parallel": true, "self": 175.50546024300752 }, "steps_from_proto": { "total": 34.28587521097893, "count": 18198, "is_parallel": true, "self": 6.428183198950364, "children": { "_process_rank_one_or_two_observation": { "total": 27.857692012028565, "count": 181980, "is_parallel": true, "self": 27.857692012028565 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001235489999089623, "count": 1, "self": 0.0001235489999089623, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 442.127694332165, "count": 698408, "is_parallel": true, "self": 15.019181211255727, "children": { "process_trajectory": { "total": 242.46786341090865, "count": 698408, "is_parallel": true, "self": 241.94557577790852, "children": { "RLTrainer._checkpoint": { "total": 0.5222876330001327, "count": 4, "is_parallel": true, "self": 0.5222876330001327 } } }, "_update_policy": { "total": 184.64064971000062, "count": 90, "is_parallel": true, "self": 53.83796470600487, "children": { "TorchPPOOptimizer.update": { "total": 130.80268500399575, "count": 4587, "is_parallel": true, "self": 130.80268500399575 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09341204499992273, "count": 1, "self": 0.0013548609999816108, "children": { "RLTrainer._checkpoint": { "total": 0.09205718399994112, "count": 1, "self": 0.09205718399994112 } } } } } } }