{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7701351642608643, "min": 0.7701351642608643, "max": 2.803462028503418, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 15257.1474609375, "min": 15257.1474609375, "max": 57574.69921875, "count": 50 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 19992.0, "max": 999952.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 19992.0, "max": 999952.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.359333038330078, "min": 0.8000254034996033, "max": 14.413833618164062, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 5729.3740234375, "min": 319.21014404296875, "max": 5816.5546875, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 19701.0, "min": 19701.0, "max": 21890.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07199227705364286, "min": 0.06561244035022123, "max": 0.0730900271766301, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.6479304934827858, "min": 0.5905119631519911, "max": 0.7146903942119132, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14571800644880806, "min": 0.13468601455583293, "max": 0.2569509458308127, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.3114620580392726, "min": 1.2421534199048492, "max": 2.312558512477314, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0264098991199996e-05, "min": 3.0264098991199996e-05, "max": 0.0029672640010912003, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0002723768909208, "min": 0.0002723768909208, "max": 0.026705376009820803, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10100880000000001, "min": 0.10100880000000001, "max": 0.19890880000000002, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.9090792000000001, "min": 0.9090792000000001, "max": 1.7901792000000003, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0339120000000015e-05, "min": 6.0339120000000015e-05, "max": 0.00494554912, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005430520800000001, "min": 0.0005430520800000001, "max": 0.04450994208, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.96969696969697, "min": 4.909090909090909, "max": 28.161616161616163, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 2769.0, "min": 486.0, "max": 3033.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.96969696969697, "min": 4.909090909090909, "max": 28.161616161616163, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 2769.0, "min": 486.0, "max": 3033.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709143429", "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", "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": "1709145930" }, "total": 2501.254097601, "count": 1, "self": 0.483875764000004, "children": { "run_training.setup": { "total": 0.07331573300007221, "count": 1, "self": 0.07331573300007221 }, "TrainerController.start_learning": { "total": 2500.696906104, "count": 1, "self": 3.0509337589451206, "children": { "TrainerController._reset_env": { "total": 3.2840729179999926, "count": 1, "self": 3.2840729179999926 }, "TrainerController.advance": { "total": 2494.261878257055, "count": 90934, "self": 1.4556786869757161, "children": { "env_step": { "total": 2492.806199570079, "count": 90934, "self": 1718.6286524540237, "children": { "SubprocessEnvManager._take_step": { "total": 772.6841080300592, "count": 90934, "self": 7.5297022020716895, "children": { "TorchPolicy.evaluate": { "total": 765.1544058279875, "count": 90934, "self": 765.1544058279875 } } }, "workers": { "total": 1.493439085996215, "count": 90934, "self": 0.0, "children": { "worker_root": { "total": 2494.7659995570298, "count": 90934, "is_parallel": true, "self": 1369.8063987130415, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005531141000005846, "count": 1, "is_parallel": true, "self": 0.003864534000058484, "children": { "_process_rank_one_or_two_observation": { "total": 0.001666606999947362, "count": 10, "is_parallel": true, "self": 0.001666606999947362 } } }, "UnityEnvironment.step": { "total": 0.03620565899996109, "count": 1, "is_parallel": true, "self": 0.0006527250000090135, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004344650000120964, "count": 1, "is_parallel": true, "self": 0.0004344650000120964 }, "communicator.exchange": { "total": 0.03309906399999818, "count": 1, "is_parallel": true, "self": 0.03309906399999818 }, "steps_from_proto": { "total": 0.0020194049999417985, "count": 1, "is_parallel": true, "self": 0.00037365099990438466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016457540000374138, "count": 10, "is_parallel": true, "self": 0.0016457540000374138 } } } } } } }, "UnityEnvironment.step": { "total": 1124.9596008439883, "count": 90933, "is_parallel": true, "self": 53.987919554974496, "children": { "UnityEnvironment._generate_step_input": { "total": 26.586953171015807, "count": 90933, "is_parallel": true, "self": 26.586953171015807 }, "communicator.exchange": { "total": 874.1602613450068, "count": 90933, "is_parallel": true, "self": 874.1602613450068 }, "steps_from_proto": { "total": 170.22446677299115, "count": 90933, "is_parallel": true, "self": 31.732260935009663, "children": { "_process_rank_one_or_two_observation": { "total": 138.4922058379815, "count": 909330, "is_parallel": true, "self": 138.4922058379815 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020630800008802908, "count": 1, "self": 0.00020630800008802908, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2466.6397112345476, "count": 3437502, "is_parallel": true, "self": 72.24239888367993, "children": { "process_trajectory": { "total": 1193.3242239358633, "count": 3437502, "is_parallel": true, "self": 1190.2611742318643, "children": { "RLTrainer._checkpoint": { "total": 3.063049703999013, "count": 20, "is_parallel": true, "self": 3.063049703999013 } } }, "_update_policy": { "total": 1201.0730884150043, "count": 454, "is_parallel": true, "self": 391.0551566559993, "children": { "TorchPPOOptimizer.update": { "total": 810.017931759005, "count": 38585, "is_parallel": true, "self": 810.017931759005 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09981486199967549, "count": 1, "self": 0.0010615769997457392, "children": { "RLTrainer._checkpoint": { "total": 0.09875328499992975, "count": 1, "self": 0.09875328499992975 } } } } } } }