{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9414846897125244, "min": 0.9414846897125244, "max": 2.837233066558838, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9610.67578125, "min": 9185.076171875, "max": 28962.474609375, "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": 12.867913246154785, "min": 0.2730344235897064, "max": 12.867913246154785, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2509.2431640625, "min": 52.422607421875, "max": 2615.4228515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06885125869245944, "min": 0.064106787175771, "max": 0.07653272599461214, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27540503476983774, "min": 0.25653607786436766, "max": 0.36889627000246217, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21730695978975764, "min": 0.13253694556781329, "max": 0.3082595127470353, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8692278391590306, "min": 0.5301477822712531, "max": 1.5412975637351765, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.890097370000006e-06, "min": 7.890097370000006e-06, "max": 0.00029169000276999994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.1560389480000026e-05, "min": 3.1560389480000026e-05, "max": 0.0013842000385999999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10263000000000001, "min": 0.10263000000000001, "max": 0.19723000000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41052000000000005, "min": 0.41052000000000005, "max": 0.9614, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014123700000000008, "min": 0.00014123700000000008, "max": 0.004861776999999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005649480000000003, "min": 0.0005649480000000003, "max": 0.023073859999999995, "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.Environment.CumulativeReward.mean": { "value": 25.227272727272727, "min": 3.6136363636363638, "max": 25.581818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 159.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.6136363636363638, "max": 25.581818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 159.0, "max": 1407.0, "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": "1733052424", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/zhangsz/anaconda3/envs/deep_rl_course/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1733052763" }, "total": 338.330125186003, "count": 1, "self": 0.21966511600476224, "children": { "run_training.setup": { "total": 0.010893323000345845, "count": 1, "self": 0.010893323000345845 }, "TrainerController.start_learning": { "total": 338.0995667469979, "count": 1, "self": 0.27753141995708575, "children": { "TrainerController._reset_env": { "total": 1.303241983998305, "count": 1, "self": 1.303241983998305 }, "TrainerController.advance": { "total": 336.46508998504214, "count": 18192, "self": 0.26074503542258753, "children": { "env_step": { "total": 244.41640083280436, "count": 18192, "self": 171.80774939095863, "children": { "SubprocessEnvManager._take_step": { "total": 72.42590474493409, "count": 18192, "self": 0.8186111925533623, "children": { "TorchPolicy.evaluate": { "total": 71.60729355238072, "count": 18192, "self": 71.60729355238072 } } }, "workers": { "total": 0.1827466969116358, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 337.2901172958118, "count": 18192, "is_parallel": true, "self": 181.64054854560527, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010098610000568442, "count": 1, "is_parallel": true, "self": 0.000308087001030799, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007017739990260452, "count": 10, "is_parallel": true, "self": 0.0007017739990260452 } } }, "UnityEnvironment.step": { "total": 0.01905548100330634, "count": 1, "is_parallel": true, "self": 0.00018817700401996262, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001389070021104999, "count": 1, "is_parallel": true, "self": 0.0001389070021104999 }, "communicator.exchange": { "total": 0.018159219998779008, "count": 1, "is_parallel": true, "self": 0.018159219998779008 }, "steps_from_proto": { "total": 0.0005691769983968697, "count": 1, "is_parallel": true, "self": 0.00013573500109487213, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004334419973019976, "count": 10, "is_parallel": true, "self": 0.0004334419973019976 } } } } } } }, "UnityEnvironment.step": { "total": 155.64956875020653, "count": 18191, "is_parallel": true, "self": 3.1611836370902893, "children": { "UnityEnvironment._generate_step_input": { "total": 1.8261456271029601, "count": 18191, "is_parallel": true, "self": 1.8261456271029601 }, "communicator.exchange": { "total": 141.4710012380965, "count": 18191, "is_parallel": true, "self": 141.4710012380965 }, "steps_from_proto": { "total": 9.191238247916772, "count": 18191, "is_parallel": true, "self": 2.1033415743513615, "children": { "_process_rank_one_or_two_observation": { "total": 7.08789667356541, "count": 181910, "is_parallel": true, "self": 7.08789667356541 } } } } } } } } } } }, "trainer_advance": { "total": 91.7879441168152, "count": 18192, "self": 0.33735308186805923, "children": { "process_trajectory": { "total": 20.096012293954118, "count": 18192, "self": 19.86077834495154, "children": { "RLTrainer._checkpoint": { "total": 0.235233949002577, "count": 4, "self": 0.235233949002577 } } }, "_update_policy": { "total": 71.35457874099302, "count": 90, "self": 21.752368117038714, "children": { "TorchPPOOptimizer.update": { "total": 49.602210623954306, "count": 4587, "self": 49.602210623954306 } } } } } } }, "trainer_threads": { "total": 5.5299824452959e-07, "count": 1, "self": 5.5299824452959e-07 }, "TrainerController._save_models": { "total": 0.05370280500210356, "count": 1, "self": 0.0005373090025386773, "children": { "RLTrainer._checkpoint": { "total": 0.05316549599956488, "count": 1, "self": 0.05316549599956488 } } } } } } }