{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9989095330238342, "min": 0.9989095330238342, "max": 2.861314535140991, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9548.576171875, "min": 9548.576171875, "max": 29302.72265625, "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": 12.877973556518555, "min": 0.408401757478714, "max": 12.877973556518555, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.204833984375, "min": 79.22994232177734, "max": 2588.5791015625, "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": 0.07060276940932918, "min": 0.06069987740344611, "max": 0.07381625237444406, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2824110776373167, "min": 0.24279950961378444, "max": 0.36049424841379124, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20584636678298315, "min": 0.14018584162740988, "max": 0.2763368057269676, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8233854671319326, "min": 0.5607433665096395, "max": 1.3816840286348382, "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": 25.704545454545453, "min": 3.772727272727273, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 166.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 3.772727272727273, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 166.0, "max": 1404.0, "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": "1721429180", "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": "1721429809" }, "total": 629.0646400109999, "count": 1, "self": 0.5494060660000741, "children": { "run_training.setup": { "total": 0.07017941999998811, "count": 1, "self": 0.07017941999998811 }, "TrainerController.start_learning": { "total": 628.4450545249999, "count": 1, "self": 0.8143869279979299, "children": { "TrainerController._reset_env": { "total": 4.7334418670000105, "count": 1, "self": 4.7334418670000105 }, "TrainerController.advance": { "total": 622.784582187002, "count": 18201, "self": 0.44084304499540394, "children": { "env_step": { "total": 622.3437391420066, "count": 18201, "self": 416.26910868799445, "children": { "SubprocessEnvManager._take_step": { "total": 205.64525106000855, "count": 18201, "self": 2.579938526003616, "children": { "TorchPolicy.evaluate": { "total": 203.06531253400493, "count": 18201, "self": 203.06531253400493 } } }, "workers": { "total": 0.4293793940036039, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 626.2882773229902, "count": 18201, "is_parallel": true, "self": 308.7479204520004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.01024064700004601, "count": 1, "is_parallel": true, "self": 0.007830945000080192, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024097019999658187, "count": 10, "is_parallel": true, "self": 0.0024097019999658187 } } }, "UnityEnvironment.step": { "total": 0.09624857699998302, "count": 1, "is_parallel": true, "self": 0.0007958910000525066, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004386779999663304, "count": 1, "is_parallel": true, "self": 0.0004386779999663304 }, "communicator.exchange": { "total": 0.09279316599997856, "count": 1, "is_parallel": true, "self": 0.09279316599997856 }, "steps_from_proto": { "total": 0.0022208419999856233, "count": 1, "is_parallel": true, "self": 0.0004108099998916259, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018100320000939973, "count": 10, "is_parallel": true, "self": 0.0018100320000939973 } } } } } } }, "UnityEnvironment.step": { "total": 317.5403568709898, "count": 18200, "is_parallel": true, "self": 14.938470472984818, "children": { "UnityEnvironment._generate_step_input": { "total": 7.212439630992776, "count": 18200, "is_parallel": true, "self": 7.212439630992776 }, "communicator.exchange": { "total": 251.66441236400368, "count": 18200, "is_parallel": true, "self": 251.66441236400368 }, "steps_from_proto": { "total": 43.72503440300852, "count": 18200, "is_parallel": true, "self": 8.64310541700172, "children": { "_process_rank_one_or_two_observation": { "total": 35.0819289860068, "count": 182000, "is_parallel": true, "self": 35.0819289860068 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00025723499993546284, "count": 1, "self": 0.00025723499993546284, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 614.6423078649717, "count": 909219, "is_parallel": true, "self": 20.87223579199315, "children": { "process_trajectory": { "total": 346.66455676397857, "count": 909219, "is_parallel": true, "self": 345.79141264497855, "children": { "RLTrainer._checkpoint": { "total": 0.8731441190000169, "count": 4, "is_parallel": true, "self": 0.8731441190000169 } } }, "_update_policy": { "total": 247.105515309, "count": 90, "is_parallel": true, "self": 79.9507351030033, "children": { "TorchPPOOptimizer.update": { "total": 167.1547802059967, "count": 4587, "is_parallel": true, "self": 167.1547802059967 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11238630800005467, "count": 1, "self": 0.001268077000077028, "children": { "RLTrainer._checkpoint": { "total": 0.11111823099997764, "count": 1, "self": 0.11111823099997764 } } } } } } }