{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8258373141288757, "min": 0.8258373141288757, "max": 2.847506046295166, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7912.34716796875, "min": 7912.34716796875, "max": 29192.630859375, "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": 12.80038070678711, "min": 0.34684571623802185, "max": 12.80038070678711, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2496.07421875, "min": 67.28807067871094, "max": 2600.479248046875, "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": 0.07154965822316145, "min": 0.06111196784982966, "max": 0.07338152895710093, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2861986328926458, "min": 0.25049444334581494, "max": 0.356385483324166, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18522895865288436, "min": 0.13049516201763434, "max": 0.2671083513136004, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7409158346115374, "min": 0.5219806480705373, "max": 1.335541756568002, "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": 25.613636363636363, "min": 3.840909090909091, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 169.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.840909090909091, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 169.0, "max": 1395.0, "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": "1696708820", "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": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696709346" }, "total": 526.7983700049999, "count": 1, "self": 0.9060613639999247, "children": { "run_training.setup": { "total": 0.046789777999947546, "count": 1, "self": 0.046789777999947546 }, "TrainerController.start_learning": { "total": 525.845518863, "count": 1, "self": 0.622770097979128, "children": { "TrainerController._reset_env": { "total": 7.870869069999799, "count": 1, "self": 7.870869069999799 }, "TrainerController.advance": { "total": 517.1878038240211, "count": 18212, "self": 0.2972240130359296, "children": { "env_step": { "total": 516.8905798109852, "count": 18212, "self": 354.65780514698486, "children": { "SubprocessEnvManager._take_step": { "total": 161.93042774900073, "count": 18212, "self": 1.5827789740137632, "children": { "TorchPolicy.evaluate": { "total": 160.34764877498696, "count": 18212, "self": 160.34764877498696 } } }, "workers": { "total": 0.302346914999589, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 524.355864914003, "count": 18212, "is_parallel": true, "self": 260.0386864730076, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023252270000284625, "count": 1, "is_parallel": true, "self": 0.0006870020004043909, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016382249996240716, "count": 10, "is_parallel": true, "self": 0.0016382249996240716 } } }, "UnityEnvironment.step": { "total": 0.0367189139999482, "count": 1, "is_parallel": true, "self": 0.0005760409994763904, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004550130001916841, "count": 1, "is_parallel": true, "self": 0.0004550130001916841 }, "communicator.exchange": { "total": 0.033351167000091664, "count": 1, "is_parallel": true, "self": 0.033351167000091664 }, "steps_from_proto": { "total": 0.002336693000188461, "count": 1, "is_parallel": true, "self": 0.00042729799997687223, "children": { "_process_rank_one_or_two_observation": { "total": 0.001909395000211589, "count": 10, "is_parallel": true, "self": 0.001909395000211589 } } } } } } }, "UnityEnvironment.step": { "total": 264.31717844099535, "count": 18211, "is_parallel": true, "self": 11.221985315048641, "children": { "UnityEnvironment._generate_step_input": { "total": 5.894398654983661, "count": 18211, "is_parallel": true, "self": 5.894398654983661 }, "communicator.exchange": { "total": 205.32908093198512, "count": 18211, "is_parallel": true, "self": 205.32908093198512 }, "steps_from_proto": { "total": 41.87171353897793, "count": 18211, "is_parallel": true, "self": 7.731201313978772, "children": { "_process_rank_one_or_two_observation": { "total": 34.140512224999156, "count": 182110, "is_parallel": true, "self": 34.140512224999156 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001678420001098857, "count": 1, "self": 0.0001678420001098857, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 512.738639983952, "count": 530548, "is_parallel": true, "self": 11.86151506993997, "children": { "process_trajectory": { "total": 283.12046174901184, "count": 530548, "is_parallel": true, "self": 281.92309063501193, "children": { "RLTrainer._checkpoint": { "total": 1.1973711139999068, "count": 4, "is_parallel": true, "self": 1.1973711139999068 } } }, "_update_policy": { "total": 217.7566631650002, "count": 90, "is_parallel": true, "self": 84.56245451800737, "children": { "TorchPPOOptimizer.update": { "total": 133.19420864699282, "count": 4584, "is_parallel": true, "self": 133.19420864699282 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16390802899991286, "count": 1, "self": 0.0012625009999283066, "children": { "RLTrainer._checkpoint": { "total": 0.16264552799998455, "count": 1, "self": 0.16264552799998455 } } } } } } }