{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.931367814540863, "min": 0.931367814540863, "max": 2.873124837875366, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8974.66015625, "min": 8974.66015625, "max": 29423.671875, "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": 11.770424842834473, "min": 0.5329627990722656, "max": 11.770424842834473, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2295.23291015625, "min": 103.39478302001953, "max": 2383.4013671875, "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": 0.06751240961759822, "min": 0.06389981430345193, "max": 0.07621380132759976, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27004963847039287, "min": 0.2555992572138077, "max": 0.3701743514558949, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18263296359309963, "min": 0.14694492110306873, "max": 0.2918724190955069, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7305318543723985, "min": 0.5877796844122749, "max": 1.4593620954775344, "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": 22.954545454545453, "min": 3.772727272727273, "max": 23.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1010.0, "min": 166.0, "max": 1290.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.954545454545453, "min": 3.772727272727273, "max": 23.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1010.0, "min": 166.0, "max": 1290.0, "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": "1677812180", "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": "1.22.4", "end_time_seconds": "1677812833" }, "total": 652.6184977419999, "count": 1, "self": 0.7928859529998817, "children": { "run_training.setup": { "total": 0.22624466700000312, "count": 1, "self": 0.22624466700000312 }, "TrainerController.start_learning": { "total": 651.599367122, "count": 1, "self": 0.9905411300070455, "children": { "TrainerController._reset_env": { "total": 8.433369784999968, "count": 1, "self": 8.433369784999968 }, "TrainerController.advance": { "total": 641.960146427993, "count": 18217, "self": 0.5402659789962172, "children": { "env_step": { "total": 641.4198804489968, "count": 18217, "self": 508.2394874399966, "children": { "SubprocessEnvManager._take_step": { "total": 132.7142186800025, "count": 18217, "self": 2.8141317690009373, "children": { "TorchPolicy.evaluate": { "total": 129.90008691100155, "count": 18217, "self": 22.495479214989587, "children": { "TorchPolicy.sample_actions": { "total": 107.40460769601196, "count": 18217, "self": 107.40460769601196 } } } } }, "workers": { "total": 0.4661743289976812, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 649.1764813680011, "count": 18217, "is_parallel": true, "self": 287.0425967500065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009485175000008894, "count": 1, "is_parallel": true, "self": 0.006546263000075214, "children": { "_process_rank_one_or_two_observation": { "total": 0.00293891199993368, "count": 10, "is_parallel": true, "self": 0.00293891199993368 } } }, "UnityEnvironment.step": { "total": 0.04760998599999766, "count": 1, "is_parallel": true, "self": 0.0008276899999941634, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048586299999442417, "count": 1, "is_parallel": true, "self": 0.00048586299999442417 }, "communicator.exchange": { "total": 0.04361148800001047, "count": 1, "is_parallel": true, "self": 0.04361148800001047 }, "steps_from_proto": { "total": 0.0026849449999986064, "count": 1, "is_parallel": true, "self": 0.0005697849999251048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021151600000735016, "count": 10, "is_parallel": true, "self": 0.0021151600000735016 } } } } } } }, "UnityEnvironment.step": { "total": 362.13388461799457, "count": 18216, "is_parallel": true, "self": 14.955476191001594, "children": { "UnityEnvironment._generate_step_input": { "total": 7.8527440449978485, "count": 18216, "is_parallel": true, "self": 7.8527440449978485 }, "communicator.exchange": { "total": 292.28112289299526, "count": 18216, "is_parallel": true, "self": 292.28112289299526 }, "steps_from_proto": { "total": 47.04454148899987, "count": 18216, "is_parallel": true, "self": 10.964707367982555, "children": { "_process_rank_one_or_two_observation": { "total": 36.07983412101731, "count": 182160, "is_parallel": true, "self": 36.07983412101731 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021572399998603942, "count": 1, "self": 0.00021572399998603942, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 636.4646155760473, "count": 642021, "is_parallel": true, "self": 16.274490189043377, "children": { "process_trajectory": { "total": 353.99679346900433, "count": 642021, "is_parallel": true, "self": 352.32719790100435, "children": { "RLTrainer._checkpoint": { "total": 1.669595567999977, "count": 4, "is_parallel": true, "self": 1.669595567999977 } } }, "_update_policy": { "total": 266.19333191799967, "count": 90, "is_parallel": true, "self": 93.06619651200043, "children": { "TorchPPOOptimizer.update": { "total": 173.12713540599924, "count": 4587, "is_parallel": true, "self": 173.12713540599924 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21509405500000867, "count": 1, "self": 0.0014129120000916373, "children": { "RLTrainer._checkpoint": { "total": 0.21368114299991703, "count": 1, "self": 0.21368114299991703 } } } } } } }