{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8186061978340149, "min": 0.8186061978340149, "max": 1.0559101104736328, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8410.3603515625, "min": 8268.572265625, "max": 10790.345703125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 299944.0, "min": 209936.0, "max": 299944.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 299944.0, "min": 209936.0, "max": 299944.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.922038078308105, "min": 11.952845573425293, "max": 12.922038078308105, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2636.095703125, "min": 2294.9462890625, "max": 2636.095703125, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06289340531380445, "min": 0.06289340531380445, "max": 0.07298895062550026, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.31446702656902226, "min": 0.2564468645221353, "max": 0.3649447531275013, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18273486009999815, "min": 0.17269556761226232, "max": 0.2061975409587224, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9136743004999908, "min": 0.6907822704490493, "max": 1.030987704793612, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.168098208000002e-06, "min": 7.168098208000002e-06, "max": 0.00012596806850800004, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.584049104000001e-05, "min": 3.584049104000001e-05, "max": 0.00056384035904, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10179200000000002, "min": 0.10179200000000002, "max": 0.131492, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5089600000000001, "min": 0.420368, "max": 0.64096, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.942080000000004e-05, "min": 9.942080000000004e-05, "max": 0.0015814508000000001, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004971040000000002, "min": 0.0004971040000000002, "max": 0.007083904000000002, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.254545454545454, "min": 23.59090909090909, "max": 25.65909090909091, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1389.0, "min": 1038.0, "max": 1394.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.254545454545454, "min": 23.59090909090909, "max": 25.65909090909091, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1389.0, "min": 1038.0, "max": 1394.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701177864", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701178121" }, "total": 257.64591268899994, "count": 1, "self": 0.6856021840001176, "children": { "run_training.setup": { "total": 0.05936170099994342, "count": 1, "self": 0.05936170099994342 }, "TrainerController.start_learning": { "total": 256.9009488039999, "count": 1, "self": 0.3805073840026125, "children": { "TrainerController._reset_env": { "total": 2.9045668460000797, "count": 1, "self": 2.9045668460000797 }, "TrainerController.advance": { "total": 253.47316530099715, "count": 9133, "self": 0.14800347099526334, "children": { "env_step": { "total": 253.3251618300019, "count": 9133, "self": 171.39293613799282, "children": { "SubprocessEnvManager._take_step": { "total": 81.77459825699498, "count": 9133, "self": 0.7997666729916091, "children": { "TorchPolicy.evaluate": { "total": 80.97483158400337, "count": 9133, "self": 80.97483158400337 } } }, "workers": { "total": 0.15762743501409204, "count": 9133, "self": 0.0, "children": { "worker_root": { "total": 256.1380643099999, "count": 9133, "is_parallel": true, "self": 126.38200379400519, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020239119999132527, "count": 1, "is_parallel": true, "self": 0.0006067859994800529, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014171260004331998, "count": 10, "is_parallel": true, "self": 0.0014171260004331998 } } }, "UnityEnvironment.step": { "total": 0.04059344400002374, "count": 1, "is_parallel": true, "self": 0.0006465980000029958, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003702849999172031, "count": 1, "is_parallel": true, "self": 0.0003702849999172031 }, "communicator.exchange": { "total": 0.03738552599998002, "count": 1, "is_parallel": true, "self": 0.03738552599998002 }, "steps_from_proto": { "total": 0.00219103500012352, "count": 1, "is_parallel": true, "self": 0.00041975999988608237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017712750002374378, "count": 10, "is_parallel": true, "self": 0.0017712750002374378 } } } } } } }, "UnityEnvironment.step": { "total": 129.7560605159947, "count": 9132, "is_parallel": true, "self": 5.707123729009709, "children": { "UnityEnvironment._generate_step_input": { "total": 2.9608065359964257, "count": 9132, "is_parallel": true, "self": 2.9608065359964257 }, "communicator.exchange": { "total": 102.44725635898658, "count": 9132, "is_parallel": true, "self": 102.44725635898658 }, "steps_from_proto": { "total": 18.64087389200199, "count": 9132, "is_parallel": true, "self": 3.5414231690879205, "children": { "_process_rank_one_or_two_observation": { "total": 15.09945072291407, "count": 91320, "is_parallel": true, "self": 15.09945072291407 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004969950000486278, "count": 1, "self": 0.0004969950000486278, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 251.32488757299438, "count": 260643, "is_parallel": true, "self": 5.929078582990769, "children": { "process_trajectory": { "total": 143.6799359830029, "count": 260643, "is_parallel": true, "self": 143.3605227300029, "children": { "RLTrainer._checkpoint": { "total": 0.31941325299999335, "count": 2, "is_parallel": true, "self": 0.31941325299999335 } } }, "_update_policy": { "total": 101.71587300700071, "count": 45, "is_parallel": true, "self": 32.16048138999463, "children": { "TorchPPOOptimizer.update": { "total": 69.55539161700608, "count": 2292, "is_parallel": true, "self": 69.55539161700608 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14221227799998815, "count": 1, "self": 0.0016194329998597823, "children": { "RLTrainer._checkpoint": { "total": 0.14059284500012836, "count": 1, "self": 0.14059284500012836 } } } } } } }