{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9200551509857178, "min": 0.9200551509857178, "max": 2.873101234436035, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8804.927734375, "min": 8804.927734375, "max": 29486.638671875, "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": 12.726469993591309, "min": 0.2774946391582489, "max": 12.726469993591309, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2481.66162109375, "min": 53.83395767211914, "max": 2583.86572265625, "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": 0.06528170926578561, "min": 0.061015011929121815, "max": 0.07393908450605041, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26112683706314244, "min": 0.24406004771648726, "max": 0.3505938972863506, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18931193266283064, "min": 0.11131235262990802, "max": 0.30539195056931645, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7572477306513226, "min": 0.44524941051963207, "max": 1.369093517170233, "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": 24.977272727272727, "min": 3.159090909090909, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 139.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.159090909090909, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 139.0, "max": 1380.0, "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": "1767753534", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=/content/ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767754331" }, "total": 796.3937473219999, "count": 1, "self": 0.6898694639996847, "children": { "run_training.setup": { "total": 0.04599590900011208, "count": 1, "self": 0.04599590900011208 }, "TrainerController.start_learning": { "total": 795.6578819490001, "count": 1, "self": 1.1669287269830875, "children": { "TrainerController._reset_env": { "total": 4.227700087999892, "count": 1, "self": 4.227700087999892 }, "TrainerController.advance": { "total": 790.1691566550169, "count": 18202, "self": 0.5180870479955502, "children": { "env_step": { "total": 789.6510696070213, "count": 18202, "self": 621.1194015069887, "children": { "SubprocessEnvManager._take_step": { "total": 168.0486321240203, "count": 18202, "self": 3.234821815000487, "children": { "TorchPolicy.evaluate": { "total": 164.8138103090198, "count": 18202, "self": 164.8138103090198 } } }, "workers": { "total": 0.48303597601238835, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 791.570497785995, "count": 18202, "is_parallel": true, "self": 345.05343592498275, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00783048400012376, "count": 1, "is_parallel": true, "self": 0.005403664000368735, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024268199997550255, "count": 10, "is_parallel": true, "self": 0.0024268199997550255 } } }, "UnityEnvironment.step": { "total": 0.053546439000001556, "count": 1, "is_parallel": true, "self": 0.00047464099998251186, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005503689999386552, "count": 1, "is_parallel": true, "self": 0.0005503689999386552 }, "communicator.exchange": { "total": 0.04881810500000938, "count": 1, "is_parallel": true, "self": 0.04881810500000938 }, "steps_from_proto": { "total": 0.0037033240000710066, "count": 1, "is_parallel": true, "self": 0.002518051999686577, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011852720003844297, "count": 10, "is_parallel": true, "self": 0.0011852720003844297 } } } } } } }, "UnityEnvironment.step": { "total": 446.5170618610123, "count": 18201, "is_parallel": true, "self": 19.009350890990163, "children": { "UnityEnvironment._generate_step_input": { "total": 9.30364803999828, "count": 18201, "is_parallel": true, "self": 9.30364803999828 }, "communicator.exchange": { "total": 348.63165669400587, "count": 18201, "is_parallel": true, "self": 348.63165669400587 }, "steps_from_proto": { "total": 69.57240623601797, "count": 18201, "is_parallel": true, "self": 13.671174704996702, "children": { "_process_rank_one_or_two_observation": { "total": 55.90123153102127, "count": 182010, "is_parallel": true, "self": 55.90123153102127 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020097500009796931, "count": 1, "self": 0.00020097500009796931, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 783.7493770350418, "count": 493594, "is_parallel": true, "self": 18.879755310137398, "children": { "process_trajectory": { "total": 442.1762329759051, "count": 493594, "is_parallel": true, "self": 441.14029127790536, "children": { "RLTrainer._checkpoint": { "total": 1.0359416979997604, "count": 4, "is_parallel": true, "self": 1.0359416979997604 } } }, "_update_policy": { "total": 322.69338874899927, "count": 90, "is_parallel": true, "self": 62.5311658879873, "children": { "TorchPPOOptimizer.update": { "total": 260.16222286101197, "count": 4587, "is_parallel": true, "self": 260.16222286101197 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09389550400010194, "count": 1, "self": 0.0010129229999620293, "children": { "RLTrainer._checkpoint": { "total": 0.09288258100013991, "count": 1, "self": 0.09288258100013991 } } } } } } }