{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9559780955314636, "min": 0.9423466920852661, "max": 2.860685348510742, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9180.2578125, "min": 9180.2578125, "max": 29359.212890625, "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": 12.940585136413574, "min": 0.5205940008163452, "max": 12.940585136413574, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.4140625, "min": 100.9952392578125, "max": 2630.055908203125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06864623890897059, "min": 0.0621134076418136, "max": 0.07064815321056955, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27458495563588237, "min": 0.2557043806243432, "max": 0.350940212164549, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23756372603569548, "min": 0.16135628377635253, "max": 0.2886821720383915, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9502549041427819, "min": 0.6454251351054101, "max": 1.4327750433893764, "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": 25.681818181818183, "min": 4.340909090909091, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1130.0, "min": 191.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.681818181818183, "min": 4.340909090909091, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1130.0, "min": 191.0, "max": 1397.0, "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": "1694787652", "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": "1694788313" }, "total": 661.1288618220001, "count": 1, "self": 0.5447846570002639, "children": { "run_training.setup": { "total": 0.06167990899984943, "count": 1, "self": 0.06167990899984943 }, "TrainerController.start_learning": { "total": 660.522397256, "count": 1, "self": 0.9525653999703536, "children": { "TrainerController._reset_env": { "total": 3.6812331500000255, "count": 1, "self": 3.6812331500000255 }, "TrainerController.advance": { "total": 655.7264971740294, "count": 18205, "self": 0.4914927450297455, "children": { "env_step": { "total": 655.2350044289997, "count": 18205, "self": 535.3472894849749, "children": { "SubprocessEnvManager._take_step": { "total": 119.45686402201522, "count": 18205, "self": 3.0539979230038625, "children": { "TorchPolicy.evaluate": { "total": 116.40286609901136, "count": 18205, "self": 116.40286609901136 } } }, "workers": { "total": 0.4308509220095402, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 657.7481986479825, "count": 18205, "is_parallel": true, "self": 286.13487882298955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008024448000014672, "count": 1, "is_parallel": true, "self": 0.0056099200000971905, "children": { "_process_rank_one_or_two_observation": { "total": 0.002414527999917482, "count": 10, "is_parallel": true, "self": 0.002414527999917482 } } }, "UnityEnvironment.step": { "total": 0.04949080899996261, "count": 1, "is_parallel": true, "self": 0.0008520869998847047, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005675570000676089, "count": 1, "is_parallel": true, "self": 0.0005675570000676089 }, "communicator.exchange": { "total": 0.0438533550000102, "count": 1, "is_parallel": true, "self": 0.0438533550000102 }, "steps_from_proto": { "total": 0.0042178100000000995, "count": 1, "is_parallel": true, "self": 0.0005538719999549357, "children": { "_process_rank_one_or_two_observation": { "total": 0.003663938000045164, "count": 10, "is_parallel": true, "self": 0.003663938000045164 } } } } } } }, "UnityEnvironment.step": { "total": 371.6133198249929, "count": 18204, "is_parallel": true, "self": 15.93926018301454, "children": { "UnityEnvironment._generate_step_input": { "total": 8.055074995997302, "count": 18204, "is_parallel": true, "self": 8.055074995997302 }, "communicator.exchange": { "total": 294.39248167995106, "count": 18204, "is_parallel": true, "self": 294.39248167995106 }, "steps_from_proto": { "total": 53.22650296603001, "count": 18204, "is_parallel": true, "self": 10.635144167015142, "children": { "_process_rank_one_or_two_observation": { "total": 42.59135879901487, "count": 182040, "is_parallel": true, "self": 42.59135879901487 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021612499995171675, "count": 1, "self": 0.00021612499995171675, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 649.1900654892713, "count": 669439, "is_parallel": true, "self": 18.29107090144953, "children": { "process_trajectory": { "total": 350.062148469824, "count": 669439, "is_parallel": true, "self": 349.00251075182314, "children": { "RLTrainer._checkpoint": { "total": 1.0596377180008858, "count": 4, "is_parallel": true, "self": 1.0596377180008858 } } }, "_update_policy": { "total": 280.83684611799777, "count": 90, "is_parallel": true, "self": 115.04731997497424, "children": { "TorchPPOOptimizer.update": { "total": 165.78952614302352, "count": 4587, "is_parallel": true, "self": 165.78952614302352 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16188540700022713, "count": 1, "self": 0.0011110800001006282, "children": { "RLTrainer._checkpoint": { "total": 0.1607743270001265, "count": 1, "self": 0.1607743270001265 } } } } } } }