{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8780262470245361, "min": 0.8780262470245361, "max": 2.8623125553131104, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8383.39453125, "min": 8383.39453125, "max": 29281.45703125, "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": 12.806297302246094, "min": 0.41006579995155334, "max": 12.806297302246094, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2497.22802734375, "min": 79.55276489257812, "max": 2584.013427734375, "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": 0.0639236945862649, "min": 0.062361227889810196, "max": 0.07462664651410546, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2556947783450596, "min": 0.24944491155924078, "max": 0.3731332325705273, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20975427658242335, "min": 0.11492868718421817, "max": 0.30926355062162175, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8390171063296934, "min": 0.4597147487368727, "max": 1.378672527331932, "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": 25.181818181818183, "min": 3.3636363636363638, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 148.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.3636363636363638, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 148.0, "max": 1403.0, "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": "1722023008", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722023471" }, "total": 462.7988276770001, "count": 1, "self": 0.4363876430001028, "children": { "run_training.setup": { "total": 0.06864870799995515, "count": 1, "self": 0.06864870799995515 }, "TrainerController.start_learning": { "total": 462.293791326, "count": 1, "self": 0.6019125009976278, "children": { "TrainerController._reset_env": { "total": 2.6404828379999685, "count": 1, "self": 2.6404828379999685 }, "TrainerController.advance": { "total": 458.95644281000233, "count": 18201, "self": 0.28833695899948, "children": { "env_step": { "total": 458.66810585100285, "count": 18201, "self": 295.42837513201107, "children": { "SubprocessEnvManager._take_step": { "total": 162.94644743299847, "count": 18201, "self": 1.51976042399167, "children": { "TorchPolicy.evaluate": { "total": 161.4266870090068, "count": 18201, "self": 161.4266870090068 } } }, "workers": { "total": 0.29328328599331144, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 461.02855202000336, "count": 18201, "is_parallel": true, "self": 234.01490595500792, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055801940000037575, "count": 1, "is_parallel": true, "self": 0.003965212000025531, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016149819999782267, "count": 10, "is_parallel": true, "self": 0.0016149819999782267 } } }, "UnityEnvironment.step": { "total": 0.03823943899999449, "count": 1, "is_parallel": true, "self": 0.0006734300000061921, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004240119999963099, "count": 1, "is_parallel": true, "self": 0.0004240119999963099 }, "communicator.exchange": { "total": 0.03511531899999909, "count": 1, "is_parallel": true, "self": 0.03511531899999909 }, "steps_from_proto": { "total": 0.0020266779999928985, "count": 1, "is_parallel": true, "self": 0.00042486500007044015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016018129999224584, "count": 10, "is_parallel": true, "self": 0.0016018129999224584 } } } } } } }, "UnityEnvironment.step": { "total": 227.01364606499544, "count": 18200, "is_parallel": true, "self": 10.278630960998612, "children": { "UnityEnvironment._generate_step_input": { "total": 5.502252617003592, "count": 18200, "is_parallel": true, "self": 5.502252617003592 }, "communicator.exchange": { "total": 176.4605281869919, "count": 18200, "is_parallel": true, "self": 176.4605281869919 }, "steps_from_proto": { "total": 34.772234300001344, "count": 18200, "is_parallel": true, "self": 6.704208549970986, "children": { "_process_rank_one_or_two_observation": { "total": 28.06802575003036, "count": 182000, "is_parallel": true, "self": 28.06802575003036 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011487100005069806, "count": 1, "self": 0.00011487100005069806, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 453.2846393199703, "count": 684610, "is_parallel": true, "self": 14.585111357945834, "children": { "process_trajectory": { "total": 250.1420755130244, "count": 684610, "is_parallel": true, "self": 249.36735328102435, "children": { "RLTrainer._checkpoint": { "total": 0.7747222320000446, "count": 4, "is_parallel": true, "self": 0.7747222320000446 } } }, "_update_policy": { "total": 188.5574524490001, "count": 90, "is_parallel": true, "self": 60.93033216000072, "children": { "TorchPPOOptimizer.update": { "total": 127.62712028899938, "count": 4587, "is_parallel": true, "self": 127.62712028899938 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0948383060000424, "count": 1, "self": 0.0012175690000049144, "children": { "RLTrainer._checkpoint": { "total": 0.09362073700003748, "count": 1, "self": 0.09362073700003748 } } } } } } }