{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.060049057006836, "min": 1.060049057006836, "max": 2.8670096397399902, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10202.9716796875, "min": 10202.9716796875, "max": 29518.73046875, "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": 12.202325820922852, "min": 0.33953574299812317, "max": 12.202325820922852, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2379.45361328125, "min": 65.86993408203125, "max": 2457.5244140625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07133774387501249, "min": 0.06277323205170558, "max": 0.07571450652766562, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28535097550004995, "min": 0.25109292820682233, "max": 0.3571948283197879, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20927149057388306, "min": 0.08799903117366792, "max": 0.2801661695298903, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8370859622955322, "min": 0.3519961246946717, "max": 1.4008308476494515, "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": 24.522727272727273, "min": 2.590909090909091, "max": 24.522727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1079.0, "min": 114.0, "max": 1310.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.522727272727273, "min": 2.590909090909091, "max": 24.522727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1079.0, "min": 114.0, "max": 1310.0, "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": "1735926550", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/home/ubuntu/unit_5/.env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1735926860" }, "total": 310.18380347500005, "count": 1, "self": 0.43665443899999445, "children": { "run_training.setup": { "total": 0.0172807640000201, "count": 1, "self": 0.0172807640000201 }, "TrainerController.start_learning": { "total": 309.72986827200003, "count": 1, "self": 0.4551827430036042, "children": { "TrainerController._reset_env": { "total": 1.3602338919999966, "count": 1, "self": 1.3602338919999966 }, "TrainerController.advance": { "total": 307.85973246699643, "count": 18220, "self": 0.2067468419868419, "children": { "env_step": { "total": 307.6529856250096, "count": 18220, "self": 240.72393246501235, "children": { "SubprocessEnvManager._take_step": { "total": 66.70466873000169, "count": 18220, "self": 1.168770885009394, "children": { "TorchPolicy.evaluate": { "total": 65.53589784499229, "count": 18220, "self": 65.53589784499229 } } }, "workers": { "total": 0.22438442999555264, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 308.90204435799535, "count": 18220, "is_parallel": true, "self": 159.44788582999576, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015269650000391266, "count": 1, "is_parallel": true, "self": 0.0004841730000180178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010427920000211088, "count": 10, "is_parallel": true, "self": 0.0010427920000211088 } } }, "UnityEnvironment.step": { "total": 0.037536633000001984, "count": 1, "is_parallel": true, "self": 0.0003397530000484039, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002044670000032056, "count": 1, "is_parallel": true, "self": 0.0002044670000032056 }, "communicator.exchange": { "total": 0.03602438899997651, "count": 1, "is_parallel": true, "self": 0.03602438899997651 }, "steps_from_proto": { "total": 0.000968023999973866, "count": 1, "is_parallel": true, "self": 0.0002123799999367293, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007556440000371367, "count": 10, "is_parallel": true, "self": 0.0007556440000371367 } } } } } } }, "UnityEnvironment.step": { "total": 149.4541585279996, "count": 18219, "is_parallel": true, "self": 4.843635084976825, "children": { "UnityEnvironment._generate_step_input": { "total": 3.2526354710061014, "count": 18219, "is_parallel": true, "self": 3.2526354710061014 }, "communicator.exchange": { "total": 125.19593399500786, "count": 18219, "is_parallel": true, "self": 125.19593399500786 }, "steps_from_proto": { "total": 16.161953977008807, "count": 18219, "is_parallel": true, "self": 3.6374101890191355, "children": { "_process_rank_one_or_two_observation": { "total": 12.524543787989671, "count": 182190, "is_parallel": true, "self": 12.524543787989671 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011827100001937652, "count": 1, "self": 0.00011827100001937652, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 306.5608576889888, "count": 297205, "is_parallel": true, "self": 4.090314293992378, "children": { "process_trajectory": { "total": 164.56862998599564, "count": 297205, "is_parallel": true, "self": 163.64327606599574, "children": { "RLTrainer._checkpoint": { "total": 0.9253539199999068, "count": 4, "is_parallel": true, "self": 0.9253539199999068 } } }, "_update_policy": { "total": 137.90191340900077, "count": 90, "is_parallel": true, "self": 46.363323287998924, "children": { "TorchPPOOptimizer.update": { "total": 91.53859012100185, "count": 4581, "is_parallel": true, "self": 91.53859012100185 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05460089899997911, "count": 1, "self": 0.0006637619999310118, "children": { "RLTrainer._checkpoint": { "total": 0.053937137000048097, "count": 1, "self": 0.053937137000048097 } } } } } } }