{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9401015043258667, "min": 0.9401015043258667, "max": 2.8579599857330322, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8934.724609375, "min": 8934.724609375, "max": 29174.0546875, "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": 13.019786834716797, "min": 0.39812135696411133, "max": 13.019786834716797, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2538.8583984375, "min": 77.23554229736328, "max": 2649.91357421875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.08081062388715937, "min": 0.06316973223013109, "max": 0.08081062388715937, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3232424955486375, "min": 0.25758081755667067, "max": 0.36772962746242815, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18673094851421373, "min": 0.11868623827410606, "max": 0.2894151388430128, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7469237940568549, "min": 0.4747449530964242, "max": 1.447075694215064, "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": 25.363636363636363, "min": 3.477272727272727, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 153.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.477272727272727, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 153.0, "max": 1416.0, "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": "1767199295", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767199723" }, "total": 428.0261840809999, "count": 1, "self": 0.6951355779999631, "children": { "run_training.setup": { "total": 0.03231672700007948, "count": 1, "self": 0.03231672700007948 }, "TrainerController.start_learning": { "total": 427.29873177599984, "count": 1, "self": 0.33690339397912794, "children": { "TrainerController._reset_env": { "total": 2.878044141999908, "count": 1, "self": 2.878044141999908 }, "TrainerController.advance": { "total": 424.0090058580206, "count": 18192, "self": 0.3409877070348557, "children": { "env_step": { "total": 307.59464393899884, "count": 18192, "self": 240.54840706600976, "children": { "SubprocessEnvManager._take_step": { "total": 66.84109468297015, "count": 18192, "self": 1.1996679799603953, "children": { "TorchPolicy.evaluate": { "total": 65.64142670300976, "count": 18192, "self": 65.64142670300976 } } }, "workers": { "total": 0.20514219001893252, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 425.419578866984, "count": 18192, "is_parallel": true, "self": 213.8699377909861, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004601091000040469, "count": 1, "is_parallel": true, "self": 0.003101664000269011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014994269997714582, "count": 10, "is_parallel": true, "self": 0.0014994269997714582 } } }, "UnityEnvironment.step": { "total": 0.052339120999931765, "count": 1, "is_parallel": true, "self": 0.0007730390002507193, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004430269998465519, "count": 1, "is_parallel": true, "self": 0.0004430269998465519 }, "communicator.exchange": { "total": 0.04868367699987175, "count": 1, "is_parallel": true, "self": 0.04868367699987175 }, "steps_from_proto": { "total": 0.002439377999962744, "count": 1, "is_parallel": true, "self": 0.0004770020000250952, "children": { "_process_rank_one_or_two_observation": { "total": 0.001962375999937649, "count": 10, "is_parallel": true, "self": 0.001962375999937649 } } } } } } }, "UnityEnvironment.step": { "total": 211.5496410759979, "count": 18191, "is_parallel": true, "self": 10.2314229259689, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2781633750153105, "count": 18191, "is_parallel": true, "self": 5.2781633750153105 }, "communicator.exchange": { "total": 160.7154700300082, "count": 18191, "is_parallel": true, "self": 160.7154700300082 }, "steps_from_proto": { "total": 35.324584745005495, "count": 18191, "is_parallel": true, "self": 6.466723082038243, "children": { "_process_rank_one_or_two_observation": { "total": 28.857861662967252, "count": 181910, "is_parallel": true, "self": 28.857861662967252 } } } } } } } } } } }, "trainer_advance": { "total": 116.0733742119869, "count": 18192, "self": 0.4041089389982062, "children": { "process_trajectory": { "total": 25.647357911987683, "count": 18192, "self": 25.081213632987556, "children": { "RLTrainer._checkpoint": { "total": 0.5661442790001274, "count": 4, "self": 0.5661442790001274 } } }, "_update_policy": { "total": 90.02190736100101, "count": 90, "self": 36.886222502008195, "children": { "TorchPPOOptimizer.update": { "total": 53.13568485899282, "count": 4587, "self": 53.13568485899282 } } } } } } }, "trainer_threads": { "total": 9.380000847158954e-07, "count": 1, "self": 9.380000847158954e-07 }, "TrainerController._save_models": { "total": 0.07477744400011943, "count": 1, "self": 0.0006580379999832076, "children": { "RLTrainer._checkpoint": { "total": 0.07411940600013622, "count": 1, "self": 0.07411940600013622 } } } } } } }