{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9257841110229492, "min": 0.9257841110229492, "max": 2.859952449798584, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8839.38671875, "min": 8839.38671875, "max": 29288.7734375, "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": 12.796330451965332, "min": 0.3423081338405609, "max": 12.796330451965332, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.284423828125, "min": 66.40777587890625, "max": 2582.486083984375, "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": 0.06811245527990417, "min": 0.06372415242744062, "max": 0.07839744837752625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2724498211196167, "min": 0.26215000273762545, "max": 0.38958819139082274, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18625947935324091, "min": 0.10772538384623534, "max": 0.28369122130029345, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7450379174129637, "min": 0.43090153538494136, "max": 1.4184561065014671, "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": 25.295454545454547, "min": 3.5, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 154.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.5, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 154.0, "max": 1380.0, "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": "1717228146", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717228613" }, "total": 466.57291897700003, "count": 1, "self": 0.43898578800002497, "children": { "run_training.setup": { "total": 0.05702353099997026, "count": 1, "self": 0.05702353099997026 }, "TrainerController.start_learning": { "total": 466.07690965800003, "count": 1, "self": 0.558622314000047, "children": { "TrainerController._reset_env": { "total": 2.888481657, "count": 1, "self": 2.888481657 }, "TrainerController.advance": { "total": 462.53671034099995, "count": 18201, "self": 0.274998319000872, "children": { "env_step": { "total": 462.2617120219991, "count": 18201, "self": 303.05580578999735, "children": { "SubprocessEnvManager._take_step": { "total": 158.91654405800995, "count": 18201, "self": 1.509023321005941, "children": { "TorchPolicy.evaluate": { "total": 157.407520737004, "count": 18201, "self": 157.407520737004 } } }, "workers": { "total": 0.2893621739917762, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 464.7787068700073, "count": 18201, "is_parallel": true, "self": 233.4357886790013, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0054419079999661335, "count": 1, "is_parallel": true, "self": 0.0038222070000983877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016197009998677458, "count": 10, "is_parallel": true, "self": 0.0016197009998677458 } } }, "UnityEnvironment.step": { "total": 0.03775749999999789, "count": 1, "is_parallel": true, "self": 0.0007914660000096774, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004363150000017413, "count": 1, "is_parallel": true, "self": 0.0004363150000017413 }, "communicator.exchange": { "total": 0.0343681800000013, "count": 1, "is_parallel": true, "self": 0.0343681800000013 }, "steps_from_proto": { "total": 0.0021615389999851686, "count": 1, "is_parallel": true, "self": 0.00037945299987995895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017820860001052097, "count": 10, "is_parallel": true, "self": 0.0017820860001052097 } } } } } } }, "UnityEnvironment.step": { "total": 231.342918191006, "count": 18200, "is_parallel": true, "self": 10.347886422016359, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5185845609956345, "count": 18200, "is_parallel": true, "self": 5.5185845609956345 }, "communicator.exchange": { "total": 180.6075913519964, "count": 18200, "is_parallel": true, "self": 180.6075913519964 }, "steps_from_proto": { "total": 34.868855855997595, "count": 18200, "is_parallel": true, "self": 6.6335756210006025, "children": { "_process_rank_one_or_two_observation": { "total": 28.235280234996992, "count": 182000, "is_parallel": true, "self": 28.235280234996992 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001383840000244163, "count": 1, "self": 0.0001383840000244163, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.1359630520029, "count": 643570, "is_parallel": true, "self": 13.899730930994053, "children": { "process_trajectory": { "total": 255.02637130000875, "count": 643570, "is_parallel": true, "self": 254.01533562600872, "children": { "RLTrainer._checkpoint": { "total": 1.011035674000027, "count": 4, "is_parallel": true, "self": 1.011035674000027 } } }, "_update_policy": { "total": 188.20986082100012, "count": 90, "is_parallel": true, "self": 59.93621927400261, "children": { "TorchPPOOptimizer.update": { "total": 128.2736415469975, "count": 4587, "is_parallel": true, "self": 128.2736415469975 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09295696200001657, "count": 1, "self": 0.0009760020000157965, "children": { "RLTrainer._checkpoint": { "total": 0.09198096000000078, "count": 1, "self": 0.09198096000000078 } } } } } } }