{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.938513994216919, "min": 0.938513994216919, "max": 2.870497226715088, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8991.90234375, "min": 8991.90234375, "max": 29459.9140625, "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": 12.801793098449707, "min": 0.4187970459461212, "max": 12.801793098449707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2496.349609375, "min": 81.24662780761719, "max": 2608.298828125, "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.Losses.PolicyLoss.mean": { "value": 0.07497299133712088, "min": 0.06361101751458859, "max": 0.07763341230456718, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2998919653484835, "min": 0.25842798589021154, "max": 0.38816706152283587, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20782803459202542, "min": 0.11604219409477368, "max": 0.30079276655234544, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8313121383681017, "min": 0.4641687763790947, "max": 1.3183099706383312, "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": 25.045454545454547, "min": 3.659090909090909, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 161.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.659090909090909, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 161.0, "max": 1404.0, "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": "1690977986", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690978469" }, "total": 483.881159517, "count": 1, "self": 0.8459211119998145, "children": { "run_training.setup": { "total": 0.04788909000035346, "count": 1, "self": 0.04788909000035346 }, "TrainerController.start_learning": { "total": 482.98734931499985, "count": 1, "self": 0.5372525829643564, "children": { "TrainerController._reset_env": { "total": 6.670224444000269, "count": 1, "self": 6.670224444000269 }, "TrainerController.advance": { "total": 475.5404042960354, "count": 18218, "self": 0.27047679601764685, "children": { "env_step": { "total": 475.26992750001773, "count": 18218, "self": 344.95124531098554, "children": { "SubprocessEnvManager._take_step": { "total": 130.03895111299153, "count": 18218, "self": 1.7384766859495357, "children": { "TorchPolicy.evaluate": { "total": 128.300474427042, "count": 18218, "self": 128.300474427042 } } }, "workers": { "total": 0.2797310760406617, "count": 18218, "self": 0.0, "children": { "worker_root": { "total": 481.3496723510134, "count": 18218, "is_parallel": true, "self": 229.05057897704683, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006419285999982094, "count": 1, "is_parallel": true, "self": 0.004943380001350306, "children": { "_process_rank_one_or_two_observation": { "total": 0.001475905998631788, "count": 10, "is_parallel": true, "self": 0.001475905998631788 } } }, "UnityEnvironment.step": { "total": 0.09346670000013546, "count": 1, "is_parallel": true, "self": 0.0016930889996729093, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004002519999630749, "count": 1, "is_parallel": true, "self": 0.0004002519999630749 }, "communicator.exchange": { "total": 0.08301451300030749, "count": 1, "is_parallel": true, "self": 0.08301451300030749 }, "steps_from_proto": { "total": 0.008358846000191988, "count": 1, "is_parallel": true, "self": 0.00044326499937596964, "children": { "_process_rank_one_or_two_observation": { "total": 0.007915581000816019, "count": 10, "is_parallel": true, "self": 0.007915581000816019 } } } } } } }, "UnityEnvironment.step": { "total": 252.29909337396657, "count": 18217, "is_parallel": true, "self": 10.841870019804446, "children": { "UnityEnvironment._generate_step_input": { "total": 5.330877130062618, "count": 18217, "is_parallel": true, "self": 5.330877130062618 }, "communicator.exchange": { "total": 199.06047987904458, "count": 18217, "is_parallel": true, "self": 199.06047987904458 }, "steps_from_proto": { "total": 37.06586634505493, "count": 18217, "is_parallel": true, "self": 6.667265038024198, "children": { "_process_rank_one_or_two_observation": { "total": 30.39860130703073, "count": 182170, "is_parallel": true, "self": 30.39860130703073 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013684399982594186, "count": 1, "self": 0.00013684399982594186, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.6966622284872, "count": 445164, "is_parallel": true, "self": 10.427117151574748, "children": { "process_trajectory": { "total": 259.33386808691284, "count": 445164, "is_parallel": true, "self": 258.143419356913, "children": { "RLTrainer._checkpoint": { "total": 1.1904487299998436, "count": 4, "is_parallel": true, "self": 1.1904487299998436 } } }, "_update_policy": { "total": 201.9356769899996, "count": 90, "is_parallel": true, "self": 77.36228323694286, "children": { "TorchPPOOptimizer.update": { "total": 124.57339375305673, "count": 4587, "is_parallel": true, "self": 124.57339375305673 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2393311480000193, "count": 1, "self": 0.004949748999933945, "children": { "RLTrainer._checkpoint": { "total": 0.23438139900008537, "count": 1, "self": 0.23438139900008537 } } } } } } }