{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6415400505065918, "min": 0.561703622341156, "max": 2.87115478515625, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6598.2392578125, "min": 5471.3193359375, "max": 29529.828125, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.415172576904297, "min": 0.31099432706832886, "max": 14.47199535369873, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2955.1103515625, "min": 60.33290100097656, "max": 2966.759033203125, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0672566971132719, "min": 0.05855719002134078, "max": 0.07890829020841778, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3362834855663595, "min": 0.2342287600853631, "max": 0.3816925527838369, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14922965277059402, "min": 0.11793587986133335, "max": 0.278657289462931, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7461482638529702, "min": 0.4717435194453334, "max": 1.393286447314655, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029919060026979997, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997302, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.996172, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986536979999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808982800000004, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.036363636363635, "min": 3.25, "max": 28.527272727272727, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1542.0, "min": 143.0, "max": 1569.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.036363636363635, "min": 3.25, "max": 28.527272727272727, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1542.0, "min": 143.0, "max": 1569.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1730585634", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1730589379" }, "total": 3744.837886224, "count": 1, "self": 0.37238802999991094, "children": { "run_training.setup": { "total": 0.04746005599997716, "count": 1, "self": 0.04746005599997716 }, "TrainerController.start_learning": { "total": 3744.418038138, "count": 1, "self": 4.81555337906093, "children": { "TrainerController._reset_env": { "total": 4.621692697999947, "count": 1, "self": 4.621692697999947 }, "TrainerController.advance": { "total": 3734.9132786089394, "count": 181878, "self": 2.266946699115124, "children": { "env_step": { "total": 3732.6463319098243, "count": 181878, "self": 2945.852760673624, "children": { "SubprocessEnvManager._take_step": { "total": 784.6992242771004, "count": 181878, "self": 11.387941191999175, "children": { "TorchPolicy.evaluate": { "total": 773.3112830851012, "count": 181878, "self": 773.3112830851012 } } }, "workers": { "total": 2.094346959099994, "count": 181878, "self": 0.0, "children": { "worker_root": { "total": 3737.442891001, "count": 181878, "is_parallel": true, "self": 1672.8620015770534, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021864210000330786, "count": 1, "is_parallel": true, "self": 0.0006658230000766707, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015205979999564079, "count": 10, "is_parallel": true, "self": 0.0015205979999564079 } } }, "UnityEnvironment.step": { "total": 0.02885359900005824, "count": 1, "is_parallel": true, "self": 0.000526874999991378, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002663970000185145, "count": 1, "is_parallel": true, "self": 0.0002663970000185145 }, "communicator.exchange": { "total": 0.02689103700004125, "count": 1, "is_parallel": true, "self": 0.02689103700004125 }, "steps_from_proto": { "total": 0.001169290000007095, "count": 1, "is_parallel": true, "self": 0.00022298799990494445, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009463020001021505, "count": 10, "is_parallel": true, "self": 0.0009463020001021505 } } } } } } }, "UnityEnvironment.step": { "total": 2064.5808894239467, "count": 181877, "is_parallel": true, "self": 62.81613091797726, "children": { "UnityEnvironment._generate_step_input": { "total": 32.092571458963675, "count": 181877, "is_parallel": true, "self": 32.092571458963675 }, "communicator.exchange": { "total": 1767.8146415619744, "count": 181877, "is_parallel": true, "self": 1767.8146415619744 }, "steps_from_proto": { "total": 201.85754548503132, "count": 181877, "is_parallel": true, "self": 38.599569197930464, "children": { "_process_rank_one_or_two_observation": { "total": 163.25797628710086, "count": 1818770, "is_parallel": true, "self": 163.25797628710086 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003727849998540478, "count": 1, "self": 0.0003727849998540478, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3731.301350774038, "count": 1721064, "is_parallel": true, "self": 19.39065765190844, "children": { "process_trajectory": { "total": 2123.051176496133, "count": 1721064, "is_parallel": true, "self": 2117.1041721281326, "children": { "RLTrainer._checkpoint": { "total": 5.947004368000307, "count": 40, "is_parallel": true, "self": 5.947004368000307 } } }, "_update_policy": { "total": 1588.8595166259965, "count": 909, "is_parallel": true, "self": 357.1475735660624, "children": { "TorchPPOOptimizer.update": { "total": 1231.7119430599341, "count": 46350, "is_parallel": true, "self": 1231.7119430599341 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06714066699987598, "count": 1, "self": 0.0010014679992309539, "children": { "RLTrainer._checkpoint": { "total": 0.06613919900064502, "count": 1, "self": 0.06613919900064502 } } } } } } }