{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0674829483032227, "min": 1.0674829483032227, "max": 2.86454701423645, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10192.3271484375, "min": 10192.3271484375, "max": 29367.3359375, "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": 12.081567764282227, "min": 0.48815402388572693, "max": 12.081567764282227, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2355.90576171875, "min": 94.7018814086914, "max": 2439.36572265625, "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": 0.06958867145152124, "min": 0.06455017384461255, "max": 0.07511025282563459, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27835468580608497, "min": 0.2591009800848505, "max": 0.37555126412817297, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19600824054841903, "min": 0.1501754716623063, "max": 0.30688845123730457, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7840329621936761, "min": 0.6007018866492252, "max": 1.5344422561865227, "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": 23.977272727272727, "min": 3.75, "max": 24.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1055.0, "min": 165.0, "max": 1303.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.977272727272727, "min": 3.75, "max": 24.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1055.0, "min": 165.0, "max": 1303.0, "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": "1721827031", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721827516" }, "total": 485.10289031799994, "count": 1, "self": 0.4354535349998514, "children": { "run_training.setup": { "total": 0.06095278600014353, "count": 1, "self": 0.06095278600014353 }, "TrainerController.start_learning": { "total": 484.60648399699994, "count": 1, "self": 0.6521972169896344, "children": { "TrainerController._reset_env": { "total": 2.787145414999941, "count": 1, "self": 2.787145414999941 }, "TrainerController.advance": { "total": 481.06775054301056, "count": 18201, "self": 0.30133144701449055, "children": { "env_step": { "total": 480.76641909599607, "count": 18201, "self": 312.60575428999573, "children": { "SubprocessEnvManager._take_step": { "total": 167.84810147199642, "count": 18201, "self": 1.6310776939922107, "children": { "TorchPolicy.evaluate": { "total": 166.2170237780042, "count": 18201, "self": 166.2170237780042 } } }, "workers": { "total": 0.3125633340039258, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 483.241308990976, "count": 18201, "is_parallel": true, "self": 241.6660443359699, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00799593100009588, "count": 1, "is_parallel": true, "self": 0.0038192010001694143, "children": { "_process_rank_one_or_two_observation": { "total": 0.004176729999926465, "count": 10, "is_parallel": true, "self": 0.004176729999926465 } } }, "UnityEnvironment.step": { "total": 0.03836967899997035, "count": 1, "is_parallel": true, "self": 0.000678721999975096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041743599990695657, "count": 1, "is_parallel": true, "self": 0.00041743599990695657 }, "communicator.exchange": { "total": 0.03479202800008352, "count": 1, "is_parallel": true, "self": 0.03479202800008352 }, "steps_from_proto": { "total": 0.0024814930000047752, "count": 1, "is_parallel": true, "self": 0.00045586099940919667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020256320005955786, "count": 10, "is_parallel": true, "self": 0.0020256320005955786 } } } } } } }, "UnityEnvironment.step": { "total": 241.5752646550061, "count": 18200, "is_parallel": true, "self": 10.908235326997556, "children": { "UnityEnvironment._generate_step_input": { "total": 5.9491585559915166, "count": 18200, "is_parallel": true, "self": 5.9491585559915166 }, "communicator.exchange": { "total": 188.23852062802234, "count": 18200, "is_parallel": true, "self": 188.23852062802234 }, "steps_from_proto": { "total": 36.47935014399468, "count": 18200, "is_parallel": true, "self": 7.20099269495654, "children": { "_process_rank_one_or_two_observation": { "total": 29.27835744903814, "count": 182000, "is_parallel": true, "self": 29.27835744903814 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018581099993753014, "count": 1, "self": 0.00018581099993753014, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.0530258589513, "count": 713111, "is_parallel": true, "self": 15.521833785943272, "children": { "process_trajectory": { "total": 264.4968262370073, "count": 713111, "is_parallel": true, "self": 263.54064874700725, "children": { "RLTrainer._checkpoint": { "total": 0.9561774900000728, "count": 4, "is_parallel": true, "self": 0.9561774900000728 } } }, "_update_policy": { "total": 195.0343658360007, "count": 90, "is_parallel": true, "self": 59.593146410003556, "children": { "TorchPPOOptimizer.update": { "total": 135.44121942599713, "count": 4587, "is_parallel": true, "self": 135.44121942599713 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09920501099986723, "count": 1, "self": 0.0010472300000401447, "children": { "RLTrainer._checkpoint": { "total": 0.09815778099982708, "count": 1, "self": 0.09815778099982708 } } } } } } }