{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9514517188072205, "min": 0.9514517188072205, "max": 2.8694143295288086, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9084.4609375, "min": 9084.4609375, "max": 29385.671875, "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": 12.859856605529785, "min": 0.3829357624053955, "max": 12.859856605529785, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2507.672119140625, "min": 74.28953552246094, "max": 2606.14990234375, "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": 0.07326638501955826, "min": 0.061232101020983, "max": 0.07601352011442941, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29306554007823304, "min": 0.26345436663969474, "max": 0.3666591217514389, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24214864434564817, "min": 0.11549933278458376, "max": 0.28559479884365024, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9685945773825927, "min": 0.461997331138335, "max": 1.2904852336528254, "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": 25.477272727272727, "min": 3.340909090909091, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 147.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.340909090909091, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 147.0, "max": 1391.0, "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": "1723362578", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723363071" }, "total": 493.50058008300005, "count": 1, "self": 0.3889668870000378, "children": { "run_training.setup": { "total": 0.0605994740000142, "count": 1, "self": 0.0605994740000142 }, "TrainerController.start_learning": { "total": 493.051013722, "count": 1, "self": 0.6407762880011205, "children": { "TrainerController._reset_env": { "total": 2.8375267270000677, "count": 1, "self": 2.8375267270000677 }, "TrainerController.advance": { "total": 489.47979094599873, "count": 18200, "self": 0.3235936309835097, "children": { "env_step": { "total": 489.1561973150152, "count": 18200, "self": 319.5763626520119, "children": { "SubprocessEnvManager._take_step": { "total": 169.2522860700085, "count": 18200, "self": 1.6687533540131199, "children": { "TorchPolicy.evaluate": { "total": 167.58353271599537, "count": 18200, "self": 167.58353271599537 } } }, "workers": { "total": 0.3275485929948445, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 491.7423064059998, "count": 18200, "is_parallel": true, "self": 246.7381489819927, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051403040000650435, "count": 1, "is_parallel": true, "self": 0.003531922000092891, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016083819999721527, "count": 10, "is_parallel": true, "self": 0.0016083819999721527 } } }, "UnityEnvironment.step": { "total": 0.040970456999957605, "count": 1, "is_parallel": true, "self": 0.0007161800000403673, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004322469999351597, "count": 1, "is_parallel": true, "self": 0.0004322469999351597 }, "communicator.exchange": { "total": 0.03763788300000215, "count": 1, "is_parallel": true, "self": 0.03763788300000215 }, "steps_from_proto": { "total": 0.00218414699997993, "count": 1, "is_parallel": true, "self": 0.00040468200040777447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017794649995721556, "count": 10, "is_parallel": true, "self": 0.0017794649995721556 } } } } } } }, "UnityEnvironment.step": { "total": 245.00415742400708, "count": 18199, "is_parallel": true, "self": 10.847270761019558, "children": { "UnityEnvironment._generate_step_input": { "total": 5.850110147997839, "count": 18199, "is_parallel": true, "self": 5.850110147997839 }, "communicator.exchange": { "total": 191.54175295699702, "count": 18199, "is_parallel": true, "self": 191.54175295699702 }, "steps_from_proto": { "total": 36.76502355799266, "count": 18199, "is_parallel": true, "self": 7.096317737958543, "children": { "_process_rank_one_or_two_observation": { "total": 29.66870582003412, "count": 181990, "is_parallel": true, "self": 29.66870582003412 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013104300001032243, "count": 1, "self": 0.00013104300001032243, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 483.5447808700037, "count": 693190, "is_parallel": true, "self": 15.090234199008478, "children": { "process_trajectory": { "total": 269.0404704939948, "count": 693190, "is_parallel": true, "self": 268.306324603995, "children": { "RLTrainer._checkpoint": { "total": 0.7341458899998088, "count": 4, "is_parallel": true, "self": 0.7341458899998088 } } }, "_update_policy": { "total": 199.41407617700042, "count": 90, "is_parallel": true, "self": 61.78580813000258, "children": { "TorchPPOOptimizer.update": { "total": 137.62826804699785, "count": 4587, "is_parallel": true, "self": 137.62826804699785 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09278871800006527, "count": 1, "self": 0.0009624010001516581, "children": { "RLTrainer._checkpoint": { "total": 0.09182631699991362, "count": 1, "self": 0.09182631699991362 } } } } } } }