{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9814606308937073, "min": 0.9814606308937073, "max": 2.867891550064087, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9392.578125, "min": 9392.578125, "max": 29401.625, "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": 12.833468437194824, "min": 0.46914955973625183, "max": 12.833468437194824, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2502.5263671875, "min": 91.0150146484375, "max": 2573.451416015625, "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": 0.07051855728608572, "min": 0.06056015055697108, "max": 0.07573349608733848, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2820742291443429, "min": 0.24224060222788432, "max": 0.36335237615390265, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1902783544478463, "min": 0.12520839474574827, "max": 0.28378061935597776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7611134177913852, "min": 0.5008335789829931, "max": 1.401134643776744, "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": 25.886363636363637, "min": 3.5, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 154.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.5, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 154.0, "max": 1387.0, "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": "1694605531", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1694606001" }, "total": 469.73889252800006, "count": 1, "self": 0.7902340439999307, "children": { "run_training.setup": { "total": 0.04359135900006095, "count": 1, "self": 0.04359135900006095 }, "TrainerController.start_learning": { "total": 468.9050671250001, "count": 1, "self": 0.5403079430080879, "children": { "TrainerController._reset_env": { "total": 4.2068873540000595, "count": 1, "self": 4.2068873540000595 }, "TrainerController.advance": { "total": 463.9178872239921, "count": 18215, "self": 0.2592089389962666, "children": { "env_step": { "total": 463.65867828499586, "count": 18215, "self": 339.52846424898314, "children": { "SubprocessEnvManager._take_step": { "total": 123.85232922299895, "count": 18215, "self": 1.7700206989914022, "children": { "TorchPolicy.evaluate": { "total": 122.08230852400754, "count": 18215, "self": 122.08230852400754 } } }, "workers": { "total": 0.2778848130137703, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 467.4199869079865, "count": 18215, "is_parallel": true, "self": 221.02906147698832, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006266584999934821, "count": 1, "is_parallel": true, "self": 0.0047227879999809375, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015437969999538836, "count": 10, "is_parallel": true, "self": 0.0015437969999538836 } } }, "UnityEnvironment.step": { "total": 0.048977503999935834, "count": 1, "is_parallel": true, "self": 0.0006369879999965633, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034273099993242795, "count": 1, "is_parallel": true, "self": 0.00034273099993242795 }, "communicator.exchange": { "total": 0.04479368099998737, "count": 1, "is_parallel": true, "self": 0.04479368099998737 }, "steps_from_proto": { "total": 0.00320410400001947, "count": 1, "is_parallel": true, "self": 0.0004227800003491211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027813239996703487, "count": 10, "is_parallel": true, "self": 0.0027813239996703487 } } } } } } }, "UnityEnvironment.step": { "total": 246.3909254309982, "count": 18214, "is_parallel": true, "self": 10.480865866994804, "children": { "UnityEnvironment._generate_step_input": { "total": 5.218154875998039, "count": 18214, "is_parallel": true, "self": 5.218154875998039 }, "communicator.exchange": { "total": 194.96777390401144, "count": 18214, "is_parallel": true, "self": 194.96777390401144 }, "steps_from_proto": { "total": 35.72413078399393, "count": 18214, "is_parallel": true, "self": 6.368286863021581, "children": { "_process_rank_one_or_two_observation": { "total": 29.355843920972347, "count": 182140, "is_parallel": true, "self": 29.355843920972347 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014497999995910504, "count": 1, "self": 0.00014497999995910504, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.54685058501855, "count": 430250, "is_parallel": true, "self": 9.573496324051007, "children": { "process_trajectory": { "total": 249.4536355059671, "count": 430250, "is_parallel": true, "self": 247.8312646819669, "children": { "RLTrainer._checkpoint": { "total": 1.6223708240001997, "count": 4, "is_parallel": true, "self": 1.6223708240001997 } } }, "_update_policy": { "total": 201.51971875500044, "count": 90, "is_parallel": true, "self": 81.43244313299647, "children": { "TorchPPOOptimizer.update": { "total": 120.08727562200397, "count": 4587, "is_parallel": true, "self": 120.08727562200397 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23983962399984193, "count": 1, "self": 0.001164929999731612, "children": { "RLTrainer._checkpoint": { "total": 0.23867469400011032, "count": 1, "self": 0.23867469400011032 } } } } } } }