{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.125892996788025, "min": 1.1205164194107056, "max": 2.872959613800049, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10799.5654296875, "min": 10799.5654296875, "max": 29453.58203125, "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": 11.686358451843262, "min": 0.3365711271762848, "max": 11.686358451843262, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2278.83984375, "min": 65.2947998046875, "max": 2379.39697265625, "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": 0.06803983609379251, "min": 0.06231939940263663, "max": 0.07646317578288361, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27215934437517003, "min": 0.24927759761054652, "max": 0.37326709721887974, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.190076331735826, "min": 0.10839343217758499, "max": 0.277444931441078, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.760305326943304, "min": 0.43357372871033995, "max": 1.3680441762302435, "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": 23.0, "min": 2.727272727272727, "max": 23.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1012.0, "min": 120.0, "max": 1262.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.0, "min": 2.727272727272727, "max": 23.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1012.0, "min": 120.0, "max": 1262.0, "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": "1768207798", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/why/miniconda3/envs/drl-310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1768208310" }, "total": 512.0579747329466, "count": 1, "self": 0.4248661785386503, "children": { "run_training.setup": { "total": 0.034796275198459625, "count": 1, "self": 0.034796275198459625 }, "TrainerController.start_learning": { "total": 511.5983122792095, "count": 1, "self": 0.7548740962520242, "children": { "TrainerController._reset_env": { "total": 3.0202297661453485, "count": 1, "self": 3.0202297661453485 }, "TrainerController.advance": { "total": 507.71557646710426, "count": 18205, "self": 0.3435579971410334, "children": { "env_step": { "total": 507.3720184699632, "count": 18205, "self": 345.5858216965571, "children": { "SubprocessEnvManager._take_step": { "total": 161.46507794689387, "count": 18205, "self": 2.187677056528628, "children": { "TorchPolicy.evaluate": { "total": 159.27740089036524, "count": 18205, "self": 159.27740089036524 } } }, "workers": { "total": 0.3211188265122473, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 510.5881370487623, "count": 18205, "is_parallel": true, "self": 262.5220075645484, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002744301687926054, "count": 1, "is_parallel": true, "self": 0.0007148361764848232, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020294655114412308, "count": 10, "is_parallel": true, "self": 0.0020294655114412308 } } }, "UnityEnvironment.step": { "total": 0.033028786070644855, "count": 1, "is_parallel": true, "self": 0.0005644829943776131, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038645602762699127, "count": 1, "is_parallel": true, "self": 0.00038645602762699127 }, "communicator.exchange": { "total": 0.030401377007365227, "count": 1, "is_parallel": true, "self": 0.030401377007365227 }, "steps_from_proto": { "total": 0.0016764700412750244, "count": 1, "is_parallel": true, "self": 0.0003489912487566471, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013274787925183773, "count": 10, "is_parallel": true, "self": 0.0013274787925183773 } } } } } } }, "UnityEnvironment.step": { "total": 248.0661294842139, "count": 18204, "is_parallel": true, "self": 10.357209996320307, "children": { "UnityEnvironment._generate_step_input": { "total": 5.582179970107973, "count": 18204, "is_parallel": true, "self": 5.582179970107973 }, "communicator.exchange": { "total": 201.53331699734554, "count": 18204, "is_parallel": true, "self": 201.53331699734554 }, "steps_from_proto": { "total": 30.593422520440072, "count": 18204, "is_parallel": true, "self": 5.819967293646187, "children": { "_process_rank_one_or_two_observation": { "total": 24.773455226793885, "count": 182040, "is_parallel": true, "self": 24.773455226793885 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022606970742344856, "count": 1, "self": 0.00022606970742344856, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 505.8317387229763, "count": 358166, "is_parallel": true, "self": 6.0662060542963445, "children": { "process_trajectory": { "total": 287.0714206555858, "count": 358166, "is_parallel": true, "self": 286.3190226745792, "children": { "RLTrainer._checkpoint": { "total": 0.7523979810066521, "count": 4, "is_parallel": true, "self": 0.7523979810066521 } } }, "_update_policy": { "total": 212.69411201309413, "count": 90, "is_parallel": true, "self": 49.609563033562154, "children": { "TorchPPOOptimizer.update": { "total": 163.08454897953197, "count": 4587, "is_parallel": true, "self": 163.08454897953197 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10740588000044227, "count": 1, "self": 0.0014524897560477257, "children": { "RLTrainer._checkpoint": { "total": 0.10595339024439454, "count": 1, "self": 0.10595339024439454 } } } } } } }