{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8970507383346558, "min": 0.8970507383346558, "max": 2.8593711853027344, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8683.451171875, "min": 8683.451171875, "max": 29282.8203125, "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": 12.968484878540039, "min": 0.4897330403327942, "max": 12.968484878540039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2528.8544921875, "min": 95.00820922851562, "max": 2630.6904296875, "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": 0.06711974147679832, "min": 0.061972181459043665, "max": 0.07335729505518662, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2684789659071933, "min": 0.24788872583617466, "max": 0.3667864752759331, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18504931149529474, "min": 0.1543298216682731, "max": 0.29394930501778926, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.740197245981179, "min": 0.6173192866730924, "max": 1.4697465250889463, "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": 25.75, "min": 3.7954545454545454, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 167.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.7954545454545454, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 167.0, "max": 1386.0, "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": "1675663729", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675664208" }, "total": 479.082033787, "count": 1, "self": 0.6594851249999465, "children": { "run_training.setup": { "total": 0.10561628999994355, "count": 1, "self": 0.10561628999994355 }, "TrainerController.start_learning": { "total": 478.3169323720001, "count": 1, "self": 0.5259841290031773, "children": { "TrainerController._reset_env": { "total": 10.980416664999893, "count": 1, "self": 10.980416664999893 }, "TrainerController.advance": { "total": 466.6086151869972, "count": 18224, "self": 0.2685847009979625, "children": { "env_step": { "total": 466.34003048599925, "count": 18224, "self": 320.88738006799383, "children": { "SubprocessEnvManager._take_step": { "total": 145.17349536100687, "count": 18224, "self": 1.5484039250051183, "children": { "TorchPolicy.evaluate": { "total": 143.62509143600175, "count": 18224, "self": 32.99328934399887, "children": { "TorchPolicy.sample_actions": { "total": 110.63180209200289, "count": 18224, "self": 110.63180209200289 } } } } }, "workers": { "total": 0.2791550569985475, "count": 18224, "self": 0.0, "children": { "worker_root": { "total": 476.6722708510001, "count": 18224, "is_parallel": true, "self": 233.65495969600693, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006077043999994203, "count": 1, "is_parallel": true, "self": 0.003617319000113639, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024597249998805637, "count": 10, "is_parallel": true, "self": 0.0024597249998805637 } } }, "UnityEnvironment.step": { "total": 0.045950253000000885, "count": 1, "is_parallel": true, "self": 0.0004504080001197508, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004138619999594084, "count": 1, "is_parallel": true, "self": 0.0004138619999594084 }, "communicator.exchange": { "total": 0.04310044999999718, "count": 1, "is_parallel": true, "self": 0.04310044999999718 }, "steps_from_proto": { "total": 0.001985532999924544, "count": 1, "is_parallel": true, "self": 0.000454122999599349, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015314100003251951, "count": 10, "is_parallel": true, "self": 0.0015314100003251951 } } } } } } }, "UnityEnvironment.step": { "total": 243.0173111549932, "count": 18223, "is_parallel": true, "self": 8.813114922991076, "children": { "UnityEnvironment._generate_step_input": { "total": 5.244223088993408, "count": 18223, "is_parallel": true, "self": 5.244223088993408 }, "communicator.exchange": { "total": 196.30156725000575, "count": 18223, "is_parallel": true, "self": 196.30156725000575 }, "steps_from_proto": { "total": 32.658405893002964, "count": 18223, "is_parallel": true, "self": 7.161243712972919, "children": { "_process_rank_one_or_two_observation": { "total": 25.497162180030045, "count": 182230, "is_parallel": true, "self": 25.497162180030045 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.9171999901554955e-05, "count": 1, "self": 3.9171999901554955e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.0273439950457, "count": 410070, "is_parallel": true, "self": 10.978435509998349, "children": { "process_trajectory": { "total": 262.85129770704737, "count": 410070, "is_parallel": true, "self": 261.3724518790474, "children": { "RLTrainer._checkpoint": { "total": 1.4788458279999759, "count": 4, "is_parallel": true, "self": 1.4788458279999759 } } }, "_update_policy": { "total": 189.197610778, "count": 90, "is_parallel": true, "self": 70.37616304000039, "children": { "TorchPPOOptimizer.update": { "total": 118.82144773799962, "count": 4587, "is_parallel": true, "self": 118.82144773799962 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2018772189999254, "count": 1, "self": 0.0011108029999604696, "children": { "RLTrainer._checkpoint": { "total": 0.20076641599996492, "count": 1, "self": 0.20076641599996492 } } } } } } }