{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0957261323928833, "min": 1.0957261323928833, "max": 2.8702428340911865, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10522.2578125, "min": 10522.2578125, "max": 29394.15625, "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": 12.900872230529785, "min": 0.38415855169296265, "max": 12.902186393737793, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.670166015625, "min": 74.5267562866211, "max": 2633.849609375, "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": 0.06715870795825121, "min": 0.06286543415433912, "max": 0.0777684613016854, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26863483183300485, "min": 0.2514617366173565, "max": 0.3744736950971213, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21775040538141538, "min": 0.12764636080429032, "max": 0.30719728966554005, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8710016215256615, "min": 0.5105854432171613, "max": 1.5359864483277004, "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": 25.15909090909091, "min": 3.522727272727273, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 155.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.522727272727273, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 155.0, "max": 1388.0, "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": "1680015971", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680016429" }, "total": 458.5522884889999, "count": 1, "self": 0.7834021879997408, "children": { "run_training.setup": { "total": 0.11898239500010277, "count": 1, "self": 0.11898239500010277 }, "TrainerController.start_learning": { "total": 457.6499039060001, "count": 1, "self": 0.5415071119887216, "children": { "TrainerController._reset_env": { "total": 8.86387649400001, "count": 1, "self": 8.86387649400001 }, "TrainerController.advance": { "total": 448.03610107801137, "count": 18224, "self": 0.2619672840107796, "children": { "env_step": { "total": 447.7741337940006, "count": 18224, "self": 324.17550820800045, "children": { "SubprocessEnvManager._take_step": { "total": 123.33750666799767, "count": 18224, "self": 2.8062897169936605, "children": { "TorchPolicy.evaluate": { "total": 120.53121695100401, "count": 18224, "self": 120.53121695100401 } } }, "workers": { "total": 0.26111891800246667, "count": 18224, "self": 0.0, "children": { "worker_root": { "total": 456.14371606599934, "count": 18224, "is_parallel": true, "self": 219.0777740800072, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005135370000061812, "count": 1, "is_parallel": true, "self": 0.0036203470000373272, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015150230000244846, "count": 10, "is_parallel": true, "self": 0.0015150230000244846 } } }, "UnityEnvironment.step": { "total": 0.0569519670000318, "count": 1, "is_parallel": true, "self": 0.0005659439999590177, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003550410000343618, "count": 1, "is_parallel": true, "self": 0.0003550410000343618 }, "communicator.exchange": { "total": 0.05439321599999403, "count": 1, "is_parallel": true, "self": 0.05439321599999403 }, "steps_from_proto": { "total": 0.0016377660000443939, "count": 1, "is_parallel": true, "self": 0.000344710000035775, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012930560000086189, "count": 10, "is_parallel": true, "self": 0.0012930560000086189 } } } } } } }, "UnityEnvironment.step": { "total": 237.06594198599214, "count": 18223, "is_parallel": true, "self": 9.368211829988923, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1995474729967555, "count": 18223, "is_parallel": true, "self": 5.1995474729967555 }, "communicator.exchange": { "total": 192.13027327200803, "count": 18223, "is_parallel": true, "self": 192.13027327200803 }, "steps_from_proto": { "total": 30.367909410998436, "count": 18223, "is_parallel": true, "self": 5.929128437987288, "children": { "_process_rank_one_or_two_observation": { "total": 24.43878097301115, "count": 182230, "is_parallel": true, "self": 24.43878097301115 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001266389999727835, "count": 1, "self": 0.0001266389999727835, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.76586376907585, "count": 388479, "is_parallel": true, "self": 9.401044334112953, "children": { "process_trajectory": { "total": 247.14504010896235, "count": 388479, "is_parallel": true, "self": 245.53049103896217, "children": { "RLTrainer._checkpoint": { "total": 1.61454907000018, "count": 4, "is_parallel": true, "self": 1.61454907000018 } } }, "_update_policy": { "total": 188.21977932600055, "count": 90, "is_parallel": true, "self": 70.23295369199877, "children": { "TorchPPOOptimizer.update": { "total": 117.98682563400178, "count": 4587, "is_parallel": true, "self": 117.98682563400178 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2082925830000022, "count": 1, "self": 0.001135712999939642, "children": { "RLTrainer._checkpoint": { "total": 0.20715687000006255, "count": 1, "self": 0.20715687000006255 } } } } } } }