{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8303590416908264, "min": 0.8303590416908264, "max": 2.838330030441284, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7891.732421875, "min": 7891.732421875, "max": 28973.671875, "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": 12.920026779174805, "min": 0.244685098528862, "max": 12.920026779174805, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.4052734375, "min": 47.468910217285156, "max": 2630.772216796875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06730676809463915, "min": 0.058867115348203145, "max": 0.07355081463852091, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2692270723785566, "min": 0.23546846139281258, "max": 0.3636518920678759, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1883113220991457, "min": 0.10898744173841003, "max": 0.28459378529120893, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7532452883965828, "min": 0.4359497669536401, "max": 1.3180105671578761, "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.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.Environment.CumulativeReward.mean": { "value": 25.431818181818183, "min": 3.3863636363636362, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 149.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.3863636363636362, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 149.0, "max": 1391.0, "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": "1759493059", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/root/.local/share/mamba/envs/u10/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1759493626" }, "total": 566.4325454320003, "count": 1, "self": 0.5924123080003483, "children": { "run_training.setup": { "total": 0.02626351099979729, "count": 1, "self": 0.02626351099979729 }, "TrainerController.start_learning": { "total": 565.8138696130002, "count": 1, "self": 0.5894996640051886, "children": { "TrainerController._reset_env": { "total": 4.037971835000008, "count": 1, "self": 4.037971835000008 }, "TrainerController.advance": { "total": 561.1125513519951, "count": 18192, "self": 0.6131085949873523, "children": { "env_step": { "total": 405.03232909600456, "count": 18192, "self": 350.7375887650378, "children": { "SubprocessEnvManager._take_step": { "total": 53.91718116699212, "count": 18192, "self": 1.9186833640167151, "children": { "TorchPolicy.evaluate": { "total": 51.99849780297541, "count": 18192, "self": 51.99849780297541 } } }, "workers": { "total": 0.37755916397463807, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 563.4224460419985, "count": 18192, "is_parallel": true, "self": 258.6500335669873, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0065490030001456034, "count": 1, "is_parallel": true, "self": 0.004371706000256381, "children": { "_process_rank_one_or_two_observation": { "total": 0.002177296999889222, "count": 10, "is_parallel": true, "self": 0.002177296999889222 } } }, "UnityEnvironment.step": { "total": 0.05017663000012362, "count": 1, "is_parallel": true, "self": 0.0006845960001555795, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041134200000669807, "count": 1, "is_parallel": true, "self": 0.00041134200000669807 }, "communicator.exchange": { "total": 0.04671395500008657, "count": 1, "is_parallel": true, "self": 0.04671395500008657 }, "steps_from_proto": { "total": 0.0023667369998747745, "count": 1, "is_parallel": true, "self": 0.0004361189999144699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019306179999603046, "count": 10, "is_parallel": true, "self": 0.0019306179999603046 } } } } } } }, "UnityEnvironment.step": { "total": 304.77241247501115, "count": 18191, "is_parallel": true, "self": 14.38866326000857, "children": { "UnityEnvironment._generate_step_input": { "total": 7.670315189007852, "count": 18191, "is_parallel": true, "self": 7.670315189007852 }, "communicator.exchange": { "total": 232.87618557802557, "count": 18191, "is_parallel": true, "self": 232.87618557802557 }, "steps_from_proto": { "total": 49.83724844796916, "count": 18191, "is_parallel": true, "self": 9.22989606801707, "children": { "_process_rank_one_or_two_observation": { "total": 40.60735237995209, "count": 181910, "is_parallel": true, "self": 40.60735237995209 } } } } } } } } } } }, "trainer_advance": { "total": 155.46711366100317, "count": 18192, "self": 0.783932319004407, "children": { "process_trajectory": { "total": 30.427612254999985, "count": 18192, "self": 29.99774509000008, "children": { "RLTrainer._checkpoint": { "total": 0.42986716499990507, "count": 4, "self": 0.42986716499990507 } } }, "_update_policy": { "total": 124.25556908699878, "count": 90, "self": 47.4765249240038, "children": { "TorchPPOOptimizer.update": { "total": 76.77904416299498, "count": 4587, "self": 76.77904416299498 } } } } } } }, "trainer_threads": { "total": 1.2069999684172217e-06, "count": 1, "self": 1.2069999684172217e-06 }, "TrainerController._save_models": { "total": 0.07384555499993439, "count": 1, "self": 0.0009142809999502788, "children": { "RLTrainer._checkpoint": { "total": 0.07293127399998411, "count": 1, "self": 0.07293127399998411 } } } } } } }