{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.367307186126709, "min": 1.367307186126709, "max": 2.8651113510131836, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14077.794921875, "min": 13444.8349609375, "max": 29247.056640625, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.222881317138672, "min": 0.522495448589325, "max": 9.222881317138672, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1881.4677734375, "min": 101.36412048339844, "max": 1881.4677734375, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.062414589457087756, "min": 0.062414589457087756, "max": 0.07077746830684334, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3120729472854388, "min": 0.2539076520154006, "max": 0.34725505865022643, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2547493478831123, "min": 0.13884203963543235, "max": 0.2914348644953148, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2737467394155615, "min": 0.5553681585417294, "max": 1.4344080175254859, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "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.Environment.CumulativeReward.mean": { "value": 19.272727272727273, "min": 3.5454545454545454, "max": 19.272727272727273, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1060.0, "min": 156.0, "max": 1060.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.272727272727273, "min": 3.5454545454545454, "max": 19.272727272727273, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1060.0, "min": 156.0, "max": 1060.0, "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": "1748551042", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748551254" }, "total": 212.15518428400003, "count": 1, "self": 0.4310215989999051, "children": { "run_training.setup": { "total": 0.022831995000046845, "count": 1, "self": 0.022831995000046845 }, "TrainerController.start_learning": { "total": 211.70133069000008, "count": 1, "self": 0.159517120990472, "children": { "TrainerController._reset_env": { "total": 3.4234088790000214, "count": 1, "self": 3.4234088790000214 }, "TrainerController.advance": { "total": 208.03368569900965, "count": 9128, "self": 0.1913733430111506, "children": { "env_step": { "total": 147.76725027800444, "count": 9128, "self": 112.04805622600713, "children": { "SubprocessEnvManager._take_step": { "total": 35.62440742999934, "count": 9128, "self": 0.6360944869931018, "children": { "TorchPolicy.evaluate": { "total": 34.988312943006235, "count": 9128, "self": 34.988312943006235 } } }, "workers": { "total": 0.09478662199796872, "count": 9128, "self": 0.0, "children": { "worker_root": { "total": 210.82024384900228, "count": 9128, "is_parallel": true, "self": 112.46342895800012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006232201999978315, "count": 1, "is_parallel": true, "self": 0.003943158000083713, "children": { "_process_rank_one_or_two_observation": { "total": 0.002289043999894602, "count": 10, "is_parallel": true, "self": 0.002289043999894602 } } }, "UnityEnvironment.step": { "total": 0.03636108500006685, "count": 1, "is_parallel": true, "self": 0.000585682999940218, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000380714000016269, "count": 1, "is_parallel": true, "self": 0.000380714000016269 }, "communicator.exchange": { "total": 0.03333390600005259, "count": 1, "is_parallel": true, "self": 0.03333390600005259 }, "steps_from_proto": { "total": 0.0020607820000577703, "count": 1, "is_parallel": true, "self": 0.00039800199999717734, "children": { "_process_rank_one_or_two_observation": { "total": 0.001662780000060593, "count": 10, "is_parallel": true, "self": 0.001662780000060593 } } } } } } }, "UnityEnvironment.step": { "total": 98.35681489100216, "count": 9127, "is_parallel": true, "self": 4.824726889991894, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7354410789988606, "count": 9127, "is_parallel": true, "self": 2.7354410789988606 }, "communicator.exchange": { "total": 75.47957133600539, "count": 9127, "is_parallel": true, "self": 75.47957133600539 }, "steps_from_proto": { "total": 15.317075586006013, "count": 9127, "is_parallel": true, "self": 2.7232227840248697, "children": { "_process_rank_one_or_two_observation": { "total": 12.593852801981143, "count": 91270, "is_parallel": true, "self": 12.593852801981143 } } } } } } } } } } }, "trainer_advance": { "total": 60.07506207799406, "count": 9128, "self": 0.19809260199156142, "children": { "process_trajectory": { "total": 13.252550439002562, "count": 9128, "self": 12.833183474002453, "children": { "RLTrainer._checkpoint": { "total": 0.4193669650001084, "count": 4, "self": 0.4193669650001084 } } }, "_update_policy": { "total": 46.62441903699994, "count": 45, "self": 18.754661011000735, "children": { "TorchPPOOptimizer.update": { "total": 27.869758025999204, "count": 2292, "self": 27.869758025999204 } } } } } } }, "trainer_threads": { "total": 8.859999525157036e-07, "count": 1, "self": 8.859999525157036e-07 }, "TrainerController._save_models": { "total": 0.084718104999979, "count": 1, "self": 0.0008424339999919539, "children": { "RLTrainer._checkpoint": { "total": 0.08387567099998705, "count": 1, "self": 0.08387567099998705 } } } } } } }