{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7881314754486084, "min": 0.7881314754486084, "max": 2.8559248447418213, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7525.0791015625, "min": 7525.0791015625, "max": 29373.1875, "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": 12.881715774536133, "min": 0.4686110317707062, "max": 12.881715774536133, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.9345703125, "min": 90.91053771972656, "max": 2614.23681640625, "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": 0.07059377441363918, "min": 0.0629040094752175, "max": 0.07607873737830304, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2823750976545567, "min": 0.25823209205797565, "max": 0.3803936868915152, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19659583555424914, "min": 0.12667658619865702, "max": 0.29041759097108655, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7863833422169966, "min": 0.5067063447946281, "max": 1.4520879548554328, "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": 25.431818181818183, "min": 3.8181818181818183, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 168.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.8181818181818183, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 168.0, "max": 1401.0, "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": "1715151399", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "1715151886" }, "total": 486.590661546, "count": 1, "self": 0.43905462599997236, "children": { "run_training.setup": { "total": 0.05711011400001098, "count": 1, "self": 0.05711011400001098 }, "TrainerController.start_learning": { "total": 486.094496806, "count": 1, "self": 0.5715493869932402, "children": { "TrainerController._reset_env": { "total": 3.5029501819999496, "count": 1, "self": 3.5029501819999496 }, "TrainerController.advance": { "total": 481.92448642700674, "count": 18199, "self": 0.2867183050054791, "children": { "env_step": { "total": 481.63776812200126, "count": 18199, "self": 316.77967766100244, "children": { "SubprocessEnvManager._take_step": { "total": 164.56268499199177, "count": 18199, "self": 1.5875232369902506, "children": { "TorchPolicy.evaluate": { "total": 162.97516175500152, "count": 18199, "self": 162.97516175500152 } } }, "workers": { "total": 0.29540546900705067, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 484.8151933199854, "count": 18199, "is_parallel": true, "self": 244.1474945639792, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056807759999628615, "count": 1, "is_parallel": true, "self": 0.003952415999890491, "children": { "_process_rank_one_or_two_observation": { "total": 0.001728360000072371, "count": 10, "is_parallel": true, "self": 0.001728360000072371 } } }, "UnityEnvironment.step": { "total": 0.0392884770000137, "count": 1, "is_parallel": true, "self": 0.0007077630000367208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043818199992529117, "count": 1, "is_parallel": true, "self": 0.00043818199992529117 }, "communicator.exchange": { "total": 0.03587924200007819, "count": 1, "is_parallel": true, "self": 0.03587924200007819 }, "steps_from_proto": { "total": 0.0022632899999734946, "count": 1, "is_parallel": true, "self": 0.0003944489999412326, "children": { "_process_rank_one_or_two_observation": { "total": 0.001868841000032262, "count": 10, "is_parallel": true, "self": 0.001868841000032262 } } } } } } }, "UnityEnvironment.step": { "total": 240.6676987560062, "count": 18198, "is_parallel": true, "self": 10.909533696015501, "children": { "UnityEnvironment._generate_step_input": { "total": 5.887894755992875, "count": 18198, "is_parallel": true, "self": 5.887894755992875 }, "communicator.exchange": { "total": 186.76764086099968, "count": 18198, "is_parallel": true, "self": 186.76764086099968 }, "steps_from_proto": { "total": 37.102629442998136, "count": 18198, "is_parallel": true, "self": 6.926197575997094, "children": { "_process_rank_one_or_two_observation": { "total": 30.176431867001043, "count": 181980, "is_parallel": true, "self": 30.176431867001043 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013012600004458363, "count": 1, "self": 0.00013012600004458363, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.83572920600375, "count": 693139, "is_parallel": true, "self": 15.402233525943302, "children": { "process_trajectory": { "total": 263.5190077590606, "count": 693139, "is_parallel": true, "self": 262.92366995106056, "children": { "RLTrainer._checkpoint": { "total": 0.5953378080000675, "count": 4, "is_parallel": true, "self": 0.5953378080000675 } } }, "_update_policy": { "total": 196.91448792099982, "count": 90, "is_parallel": true, "self": 63.466138818000104, "children": { "TorchPPOOptimizer.update": { "total": 133.4483491029997, "count": 4587, "is_parallel": true, "self": 133.4483491029997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09538068400001976, "count": 1, "self": 0.0010170860000471293, "children": { "RLTrainer._checkpoint": { "total": 0.09436359799997263, "count": 1, "self": 0.09436359799997263 } } } } } } }