{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9003983736038208, "min": 0.9003983736038208, "max": 2.8632564544677734, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8606.908203125, "min": 8606.908203125, "max": 29291.11328125, "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": 12.953564643859863, "min": 0.3370801508426666, "max": 12.953564643859863, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2525.945068359375, "min": 65.39354705810547, "max": 2635.3916015625, "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.Losses.PolicyLoss.mean": { "value": 0.06644027001839634, "min": 0.06290411336236752, "max": 0.0737800511965236, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26576108007358534, "min": 0.26576108007358534, "max": 0.368900255982618, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19853696259943876, "min": 0.14490284776433793, "max": 0.29777756362569097, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.794147850397755, "min": 0.5796113910573517, "max": 1.4128645474419876, "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": 25.454545454545453, "min": 3.8636363636363638, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 170.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.8636363636363638, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 170.0, "max": 1408.0, "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": "1680950474", "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": "1680950948" }, "total": 474.13908918899983, "count": 1, "self": 0.4365269999998418, "children": { "run_training.setup": { "total": 0.21208011099997748, "count": 1, "self": 0.21208011099997748 }, "TrainerController.start_learning": { "total": 473.490482078, "count": 1, "self": 0.6459887600306047, "children": { "TrainerController._reset_env": { "total": 4.120887433000007, "count": 1, "self": 4.120887433000007 }, "TrainerController.advance": { "total": 468.5892989299691, "count": 18202, "self": 0.3125379319608328, "children": { "env_step": { "total": 468.2767609980083, "count": 18202, "self": 342.0584186450071, "children": { "SubprocessEnvManager._take_step": { "total": 125.90433915601716, "count": 18202, "self": 1.8486778180458714, "children": { "TorchPolicy.evaluate": { "total": 124.05566133797129, "count": 18202, "self": 124.05566133797129 } } }, "workers": { "total": 0.3140031969840038, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 471.8396908940049, "count": 18202, "is_parallel": true, "self": 213.56475714701673, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005697615000144651, "count": 1, "is_parallel": true, "self": 0.004314709000482253, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013829059996623982, "count": 10, "is_parallel": true, "self": 0.0013829059996623982 } } }, "UnityEnvironment.step": { "total": 0.034089907000179664, "count": 1, "is_parallel": true, "self": 0.000576083000169092, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003010610000728775, "count": 1, "is_parallel": true, "self": 0.0003010610000728775 }, "communicator.exchange": { "total": 0.031382965999910084, "count": 1, "is_parallel": true, "self": 0.031382965999910084 }, "steps_from_proto": { "total": 0.001829797000027611, "count": 1, "is_parallel": true, "self": 0.0003940720000628062, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014357249999648047, "count": 10, "is_parallel": true, "self": 0.0014357249999648047 } } } } } } }, "UnityEnvironment.step": { "total": 258.27493374698815, "count": 18201, "is_parallel": true, "self": 10.120595362033328, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4199880459837, "count": 18201, "is_parallel": true, "self": 5.4199880459837 }, "communicator.exchange": { "total": 210.2904440639818, "count": 18201, "is_parallel": true, "self": 210.2904440639818 }, "steps_from_proto": { "total": 32.44390627498933, "count": 18201, "is_parallel": true, "self": 6.638567184979365, "children": { "_process_rank_one_or_two_observation": { "total": 25.805339090009966, "count": 182010, "is_parallel": true, "self": 25.805339090009966 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014966700018703705, "count": 1, "self": 0.00014966700018703705, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.8875299040162, "count": 438670, "is_parallel": true, "self": 10.630380675969036, "children": { "process_trajectory": { "total": 259.8771092250463, "count": 438670, "is_parallel": true, "self": 259.10009811904615, "children": { "RLTrainer._checkpoint": { "total": 0.7770111060001454, "count": 4, "is_parallel": true, "self": 0.7770111060001454 } } }, "_update_policy": { "total": 194.3800400030009, "count": 90, "is_parallel": true, "self": 66.6828041780077, "children": { "TorchPPOOptimizer.update": { "total": 127.69723582499319, "count": 4587, "is_parallel": true, "self": 127.69723582499319 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13415728800009674, "count": 1, "self": 0.001016040000195062, "children": { "RLTrainer._checkpoint": { "total": 0.13314124799990168, "count": 1, "self": 0.13314124799990168 } } } } } } }