{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8081252574920654, "min": 0.7592588067054749, "max": 2.8668529987335205, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8187.1171875, "min": 7207.64404296875, "max": 29390.9765625, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.674982070922852, "min": 0.41822054982185364, "max": 13.674982070922852, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2666.62158203125, "min": 81.1347885131836, "max": 2784.720703125, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06583968433865355, "min": 0.059713627075361014, "max": 0.07513578982262498, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2633587373546142, "min": 0.23885450830144406, "max": 0.3756789491131249, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17023806672031971, "min": 0.13393413763397427, "max": 0.29431553637864544, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6809522668812789, "min": 0.5357365505358971, "max": 1.330331102013588, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.891098702999994e-06, "min": 3.891098702999994e-06, "max": 0.000295941001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5564394811999976e-05, "min": 1.5564394811999976e-05, "max": 0.0014425800191399996, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101297, "min": 0.101297, "max": 0.19864700000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405188, "min": 0.405188, "max": 0.98086, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999992e-05, "min": 7.472029999999992e-05, "max": 0.004932485299999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999966, "min": 0.00029888119999999966, "max": 0.024044914, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.363636363636363, "min": 3.75, "max": 27.363636363636363, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1204.0, "min": 165.0, "max": 1466.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.363636363636363, "min": 3.75, "max": 27.363636363636363, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1204.0, "min": 165.0, "max": 1466.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677662876", "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 --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.14.0a0+410ce96", "numpy_version": "1.22.2", "end_time_seconds": "1677664155" }, "total": 1279.36852745153, "count": 1, "self": 0.4306524973362684, "children": { "run_training.setup": { "total": 0.1224447749555111, "count": 1, "self": 0.1224447749555111 }, "TrainerController.start_learning": { "total": 1278.8154301792383, "count": 1, "self": 1.4399392753839493, "children": { "TrainerController._reset_env": { "total": 2.4533580616116524, "count": 1, "self": 2.4533580616116524 }, "TrainerController.advance": { "total": 1274.732973081991, "count": 36400, "self": 0.6892418097704649, "children": { "env_step": { "total": 1274.0437312722206, "count": 36400, "self": 983.8605251591653, "children": { "SubprocessEnvManager._take_step": { "total": 289.47814553417265, "count": 36400, "self": 4.496531993150711, "children": { "TorchPolicy.evaluate": { "total": 284.98161354102194, "count": 36400, "self": 58.23723844997585, "children": { "TorchPolicy.sample_actions": { "total": 226.7443750910461, "count": 36400, "self": 226.7443750910461 } } } } }, "workers": { "total": 0.7050605788826942, "count": 36400, "self": 0.0, "children": { "worker_root": { "total": 1276.4965076539665, "count": 36400, "is_parallel": true, "self": 565.9918410908431, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00247807614505291, "count": 1, "is_parallel": true, "self": 0.0007794871926307678, "children": { "_process_rank_one_or_two_observation": { "total": 0.001698588952422142, "count": 10, "is_parallel": true, "self": 0.001698588952422142 } } }, "UnityEnvironment.step": { "total": 0.04465261474251747, "count": 1, "is_parallel": true, "self": 0.0006303507834672928, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006036963313817978, "count": 1, "is_parallel": true, "self": 0.0006036963313817978 }, "communicator.exchange": { "total": 0.04137147590517998, "count": 1, "is_parallel": true, "self": 0.04137147590517998 }, "steps_from_proto": { "total": 0.0020470917224884033, "count": 1, "is_parallel": true, "self": 0.0004936568439006805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015534348785877228, "count": 10, "is_parallel": true, "self": 0.0015534348785877228 } } } } } } }, "UnityEnvironment.step": { "total": 710.5046665631235, "count": 36399, "is_parallel": true, "self": 31.269173914566636, "children": { "UnityEnvironment._generate_step_input": { "total": 17.0828071590513, "count": 36399, "is_parallel": true, "self": 17.0828071590513 }, "communicator.exchange": { "total": 565.58447496593, "count": 36399, "is_parallel": true, "self": 565.58447496593 }, "steps_from_proto": { "total": 96.56821052357554, "count": 36399, "is_parallel": true, "self": 20.442621380090714, "children": { "_process_rank_one_or_two_observation": { "total": 76.12558914348483, "count": 363990, "is_parallel": true, "self": 76.12558914348483 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002613607794046402, "count": 1, "self": 0.0002613607794046402, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1270.8396374620497, "count": 500863, "is_parallel": true, "self": 12.531119368970394, "children": { "process_trajectory": { "total": 707.269273608923, "count": 500863, "is_parallel": true, "self": 704.9831691123545, "children": { "RLTrainer._checkpoint": { "total": 2.2861044965684414, "count": 8, "is_parallel": true, "self": 2.2861044965684414 } } }, "_update_policy": { "total": 551.0392444841564, "count": 181, "is_parallel": true, "self": 135.26695251464844, "children": { "TorchPPOOptimizer.update": { "total": 415.77229196950793, "count": 9228, "is_parallel": true, "self": 415.77229196950793 } } } } } } } } }, "TrainerController._save_models": { "total": 0.18889839947223663, "count": 1, "self": 0.00700913742184639, "children": { "RLTrainer._checkpoint": { "total": 0.18188926205039024, "count": 1, "self": 0.18188926205039024 } } } } } } }