{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0957363843917847, "min": 1.0957363843917847, "max": 2.849642753601074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9678.6396484375, "min": 9678.6396484375, "max": 31440.107421875, "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.Step.mean": { "value": 199800.0, "min": 9800.0, "max": 199800.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199800.0, "min": 9800.0, "max": 199800.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.482769966125488, "min": 0.389544278383255, "max": 12.482769966125488, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 624.1384887695312, "min": 19.087669372558594, "max": 624.1384887695312, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.38, "min": 3.693877551020408, "max": 24.84, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1219.0, "min": 181.0, "max": 1242.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.38, "min": 3.693877551020408, "max": 24.84, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1219.0, "min": 181.0, "max": 1242.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06480660689190057, "min": 0.05863059075993221, "max": 0.07388876557496249, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2592264275676023, "min": 0.23452236303972884, "max": 0.36944382787481245, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20724252589485226, "min": 0.1440576102000241, "max": 0.287794894958828, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.828970103579409, "min": 0.5762304408000964, "max": 1.4084345534736034, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.950097350000008e-06, "min": 7.950097350000008e-06, "max": 0.00029175000274999995, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.180038940000003e-05, "min": 3.180038940000003e-05, "max": 0.0013845000385, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10265, "min": 0.10265, "max": 0.19725000000000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4106, "min": 0.4106, "max": 0.9615, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014223500000000013, "min": 0.00014223500000000013, "max": 0.004862775, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005689400000000005, "min": 0.0005689400000000005, "max": 0.023078849999999998, "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": "1676896906", "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": "1676897363" }, "total": 457.367736304, "count": 1, "self": 0.40621549499996945, "children": { "run_training.setup": { "total": 0.18221349999998893, "count": 1, "self": 0.18221349999998893 }, "TrainerController.start_learning": { "total": 456.77930730900005, "count": 1, "self": 0.5282974679996641, "children": { "TrainerController._reset_env": { "total": 9.044605313000034, "count": 1, "self": 9.044605313000034 }, "TrainerController.advance": { "total": 447.08655201100055, "count": 18212, "self": 0.283805839002639, "children": { "env_step": { "total": 446.8027461719979, "count": 18212, "self": 292.45729088797987, "children": { "SubprocessEnvManager._take_step": { "total": 154.07393198100806, "count": 18212, "self": 1.5030741130132128, "children": { "TorchPolicy.evaluate": { "total": 152.57085786799485, "count": 18212, "self": 35.15360209999369, "children": { "TorchPolicy.sample_actions": { "total": 117.41725576800116, "count": 18212, "self": 117.41725576800116 } } } } }, "workers": { "total": 0.2715233030099853, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 455.2804496790076, "count": 18212, "is_parallel": true, "self": 216.87443295401397, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0064261009999881935, "count": 1, "is_parallel": true, "self": 0.004096816999890507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023292840000976867, "count": 10, "is_parallel": true, "self": 0.0023292840000976867 } } }, "UnityEnvironment.step": { "total": 0.03874918499991509, "count": 1, "is_parallel": true, "self": 0.000554188999899452, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003313879999495839, "count": 1, "is_parallel": true, "self": 0.0003313879999495839 }, "communicator.exchange": { "total": 0.035616284000070664, "count": 1, "is_parallel": true, "self": 0.035616284000070664 }, "steps_from_proto": { "total": 0.0022473239999953876, "count": 1, "is_parallel": true, "self": 0.0004434669999682228, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018038570000271648, "count": 10, "is_parallel": true, "self": 0.0018038570000271648 } } } } } } }, "UnityEnvironment.step": { "total": 238.4060167249936, "count": 18211, "is_parallel": true, "self": 9.53180797202674, "children": { "UnityEnvironment._generate_step_input": { "total": 5.567055799991294, "count": 18211, "is_parallel": true, "self": 5.567055799991294 }, "communicator.exchange": { "total": 190.95423976098982, "count": 18211, "is_parallel": true, "self": 190.95423976098982 }, "steps_from_proto": { "total": 32.35291319198575, "count": 18211, "is_parallel": true, "self": 7.0060446799647025, "children": { "_process_rank_one_or_two_observation": { "total": 25.346868512021047, "count": 182110, "is_parallel": true, "self": 25.346868512021047 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00026620199992066773, "count": 1, "self": 0.00026620199992066773, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.32295641398196, "count": 339008, "is_parallel": true, "self": 8.448316760924968, "children": { "process_trajectory": { "total": 204.50525988505694, "count": 339008, "is_parallel": true, "self": 203.38160973805714, "children": { "RLTrainer._checkpoint": { "total": 1.1236501469998075, "count": 4, "is_parallel": true, "self": 1.1236501469998075 } } }, "_update_policy": { "total": 231.36937976800004, "count": 90, "is_parallel": true, "self": 69.09464373500555, "children": { "TorchPPOOptimizer.update": { "total": 162.2747360329945, "count": 4590, "is_parallel": true, "self": 162.2747360329945 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1195863149998786, "count": 1, "self": 0.0008663209998758248, "children": { "RLTrainer._checkpoint": { "total": 0.11871999400000277, "count": 1, "self": 0.11871999400000277 } } } } } } }