{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6801900863647461, "min": 0.6801900863647461, "max": 2.8629424571990967, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6464.5263671875, "min": 6464.5263671875, "max": 29224.916015625, "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": 12.303868293762207, "min": 0.37539854645729065, "max": 12.303868293762207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2399.25439453125, "min": 72.82731628417969, "max": 2460.80517578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07057325804307052, "min": 0.062214809543494246, "max": 0.07496518599217263, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2822930321722821, "min": 0.24885923817397698, "max": 0.37330044252460126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21196117829166206, "min": 0.11631287240615004, "max": 0.28842891612473653, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8478447131666482, "min": 0.46525148962460017, "max": 1.4421445806236828, "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": 25.022727272727273, "min": 3.4318181818181817, "max": 25.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 151.0, "max": 1320.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 3.4318181818181817, "max": 25.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 151.0, "max": 1320.0, "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": "1763326662", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/home/maksym/.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": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1763326848" }, "total": 185.6915301840054, "count": 1, "self": 0.217309458013915, "children": { "run_training.setup": { "total": 0.027028378994145896, "count": 1, "self": 0.027028378994145896 }, "TrainerController.start_learning": { "total": 185.44719234699733, "count": 1, "self": 0.23504491398489336, "children": { "TrainerController._reset_env": { "total": 1.1216209449994494, "count": 1, "self": 1.1216209449994494 }, "TrainerController.advance": { "total": 184.0380101910123, "count": 18192, "self": 0.2496810495504178, "children": { "env_step": { "total": 128.6817856869675, "count": 18192, "self": 95.01767846188159, "children": { "SubprocessEnvManager._take_step": { "total": 33.51250725147838, "count": 18192, "self": 0.7172282340543461, "children": { "TorchPolicy.evaluate": { "total": 32.795279017424036, "count": 18192, "self": 32.795279017424036 } } }, "workers": { "total": 0.1515999736075173, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 185.04038041886815, "count": 18192, "is_parallel": true, "self": 104.11564266916685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009754790007718839, "count": 1, "is_parallel": true, "self": 0.00024554799892939627, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007299310018424876, "count": 10, "is_parallel": true, "self": 0.0007299310018424876 } } }, "UnityEnvironment.step": { "total": 0.01914711300196359, "count": 1, "is_parallel": true, "self": 0.0002314770026714541, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014973599900258705, "count": 1, "is_parallel": true, "self": 0.00014973599900258705 }, "communicator.exchange": { "total": 0.0181040600000415, "count": 1, "is_parallel": true, "self": 0.0181040600000415 }, "steps_from_proto": { "total": 0.0006618400002480485, "count": 1, "is_parallel": true, "self": 0.00019359199359314516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004682480066549033, "count": 10, "is_parallel": true, "self": 0.0004682480066549033 } } } } } } }, "UnityEnvironment.step": { "total": 80.92473774970131, "count": 18191, "is_parallel": true, "self": 3.4350920092329034, "children": { "UnityEnvironment._generate_step_input": { "total": 1.6936843445218983, "count": 18191, "is_parallel": true, "self": 1.6936843445218983 }, "communicator.exchange": { "total": 66.2781171287861, "count": 18191, "is_parallel": true, "self": 66.2781171287861 }, "steps_from_proto": { "total": 9.517844267160399, "count": 18191, "is_parallel": true, "self": 1.9523262051006895, "children": { "_process_rank_one_or_two_observation": { "total": 7.565518062059709, "count": 181910, "is_parallel": true, "self": 7.565518062059709 } } } } } } } } } } }, "trainer_advance": { "total": 55.106543454494386, "count": 18192, "self": 0.30331364481389755, "children": { "process_trajectory": { "total": 12.190065785653132, "count": 18192, "self": 11.947112989662855, "children": { "RLTrainer._checkpoint": { "total": 0.24295279599027708, "count": 4, "self": 0.24295279599027708 } } }, "_update_policy": { "total": 42.613164024027355, "count": 90, "self": 17.41044415182114, "children": { "TorchPPOOptimizer.update": { "total": 25.202719872206217, "count": 4587, "self": 25.202719872206217 } } } } } } }, "trainer_threads": { "total": 4.579997039400041e-07, "count": 1, "self": 4.579997039400041e-07 }, "TrainerController._save_models": { "total": 0.05251583900098922, "count": 1, "self": 0.0006255069965845905, "children": { "RLTrainer._checkpoint": { "total": 0.05189033200440463, "count": 1, "self": 0.05189033200440463 } } } } } } }