{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0515573024749756, "min": 1.0515573024749756, "max": 2.843594551086426, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9994.0009765625, "min": 9994.0009765625, "max": 29027.412109375, "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": 12.389756202697754, "min": 0.4428372085094452, "max": 12.389756202697754, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2416.00244140625, "min": 85.91041564941406, "max": 2466.55224609375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06547318841195174, "min": 0.06381633541850354, "max": 0.0750572407038371, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26189275364780695, "min": 0.25672518312885406, "max": 0.3752862035191855, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21677450740746423, "min": 0.1471010061099614, "max": 0.28425290082015237, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8670980296298569, "min": 0.5884040244398456, "max": 1.4212645041007619, "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": 24.886363636363637, "min": 3.7954545454545454, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1095.0, "min": 167.0, "max": 1347.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.886363636363637, "min": 3.7954545454545454, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1095.0, "min": 167.0, "max": 1347.0, "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": "1785289295", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785289816" }, "total": 521.761878156, "count": 1, "self": 0.7926807240000926, "children": { "run_training.setup": { "total": 0.027559894999967582, "count": 1, "self": 0.027559894999967582 }, "TrainerController.start_learning": { "total": 520.9416375369999, "count": 1, "self": 0.4527568550026899, "children": { "TrainerController._reset_env": { "total": 2.107577545999902, "count": 1, "self": 2.107577545999902 }, "TrainerController.advance": { "total": 518.2976683449974, "count": 18192, "self": 0.48256433098390517, "children": { "env_step": { "total": 386.9294669400151, "count": 18192, "self": 304.593405723012, "children": { "SubprocessEnvManager._take_step": { "total": 82.06333522700197, "count": 18192, "self": 1.5215975980008807, "children": { "TorchPolicy.evaluate": { "total": 80.54173762900109, "count": 18192, "self": 80.54173762900109 } } }, "workers": { "total": 0.27272599000116315, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 518.7674421470012, "count": 18192, "is_parallel": true, "self": 252.04223425600685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023198639999009174, "count": 1, "is_parallel": true, "self": 0.0007016360000307031, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016182279998702143, "count": 10, "is_parallel": true, "self": 0.0016182279998702143 } } }, "UnityEnvironment.step": { "total": 0.0424263229999724, "count": 1, "is_parallel": true, "self": 0.000702040999840392, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000502890000007028, "count": 1, "is_parallel": true, "self": 0.000502890000007028 }, "communicator.exchange": { "total": 0.039060823999989225, "count": 1, "is_parallel": true, "self": 0.039060823999989225 }, "steps_from_proto": { "total": 0.002160568000135754, "count": 1, "is_parallel": true, "self": 0.00043411400042714376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017264539997086104, "count": 10, "is_parallel": true, "self": 0.0017264539997086104 } } } } } } }, "UnityEnvironment.step": { "total": 266.7252078909944, "count": 18191, "is_parallel": true, "self": 11.76889271098048, "children": { "UnityEnvironment._generate_step_input": { "total": 6.578039031015351, "count": 18191, "is_parallel": true, "self": 6.578039031015351 }, "communicator.exchange": { "total": 204.87502609001558, "count": 18191, "is_parallel": true, "self": 204.87502609001558 }, "steps_from_proto": { "total": 43.503250058982985, "count": 18191, "is_parallel": true, "self": 7.470885767958407, "children": { "_process_rank_one_or_two_observation": { "total": 36.03236429102458, "count": 181910, "is_parallel": true, "self": 36.03236429102458 } } } } } } } } } } }, "trainer_advance": { "total": 130.8856370739984, "count": 18192, "self": 0.5892023189921929, "children": { "process_trajectory": { "total": 26.942717164005444, "count": 18192, "self": 26.476052637005296, "children": { "RLTrainer._checkpoint": { "total": 0.46666452700014815, "count": 4, "self": 0.46666452700014815 } } }, "_update_policy": { "total": 103.35371759100076, "count": 90, "self": 41.64550412899439, "children": { "TorchPPOOptimizer.update": { "total": 61.70821346200637, "count": 4587, "self": 61.70821346200637 } } } } } } }, "trainer_threads": { "total": 1.2860000424552709e-06, "count": 1, "self": 1.2860000424552709e-06 }, "TrainerController._save_models": { "total": 0.08363350499985245, "count": 1, "self": 0.0007713909997164592, "children": { "RLTrainer._checkpoint": { "total": 0.08286211400013599, "count": 1, "self": 0.08286211400013599 } } } } } } }