{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0116833448410034, "min": 0.9971953630447388, "max": 2.8665971755981445, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9704.06640625, "min": 9704.06640625, "max": 29482.953125, "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": 12.466856002807617, "min": 0.3310558795928955, "max": 12.466856002807617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2431.036865234375, "min": 64.22483825683594, "max": 2506.0009765625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07188957237642671, "min": 0.06356663231089638, "max": 0.07741610596855811, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28755828950570683, "min": 0.2542665292435855, "max": 0.38039345277859093, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19307607291814158, "min": 0.10863881741248654, "max": 0.2738286481038028, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7723042916725663, "min": 0.4345552696499462, "max": 1.365216148542423, "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": 24.84090909090909, "min": 3.3181818181818183, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 146.0, "max": 1345.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 3.3181818181818183, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 146.0, "max": 1345.0, "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": "1763065346", "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.x86_64 --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": "1763065855" }, "total": 508.80948540500003, "count": 1, "self": 0.4251426589999028, "children": { "run_training.setup": { "total": 0.02401290199986761, "count": 1, "self": 0.02401290199986761 }, "TrainerController.start_learning": { "total": 508.36032984400026, "count": 1, "self": 0.6683504460347649, "children": { "TrainerController._reset_env": { "total": 1.5665997819996846, "count": 1, "self": 1.5665997819996846 }, "TrainerController.advance": { "total": 506.03771932996597, "count": 18207, "self": 0.29221425695686776, "children": { "env_step": { "total": 505.7455050730091, "count": 18207, "self": 409.4896103779597, "children": { "SubprocessEnvManager._take_step": { "total": 95.94057904400552, "count": 18207, "self": 1.5299809989674031, "children": { "TorchPolicy.evaluate": { "total": 94.41059804503811, "count": 18207, "self": 94.41059804503811 } } }, "workers": { "total": 0.3153156510438748, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 506.2505358809981, "count": 18207, "is_parallel": true, "self": 214.5794308800182, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020144610002716945, "count": 1, "is_parallel": true, "self": 0.0006486239994956122, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013658370007760823, "count": 10, "is_parallel": true, "self": 0.0013658370007760823 } } }, "UnityEnvironment.step": { "total": 0.03782622500011712, "count": 1, "is_parallel": true, "self": 0.0009727299998303351, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031563600032313843, "count": 1, "is_parallel": true, "self": 0.00031563600032313843 }, "communicator.exchange": { "total": 0.033854938999866135, "count": 1, "is_parallel": true, "self": 0.033854938999866135 }, "steps_from_proto": { "total": 0.0026829200000975106, "count": 1, "is_parallel": true, "self": 0.0006309419991339382, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020519780009635724, "count": 10, "is_parallel": true, "self": 0.0020519780009635724 } } } } } } }, "UnityEnvironment.step": { "total": 291.6711050009799, "count": 18206, "is_parallel": true, "self": 12.474938645011207, "children": { "UnityEnvironment._generate_step_input": { "total": 6.573532565011192, "count": 18206, "is_parallel": true, "self": 6.573532565011192 }, "communicator.exchange": { "total": 227.18403762098433, "count": 18206, "is_parallel": true, "self": 227.18403762098433 }, "steps_from_proto": { "total": 45.43859616997315, "count": 18206, "is_parallel": true, "self": 9.29418183301732, "children": { "_process_rank_one_or_two_observation": { "total": 36.14441433695583, "count": 182060, "is_parallel": true, "self": 36.14441433695583 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.746699970492045e-05, "count": 1, "self": 9.746699970492045e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 504.01710302892343, "count": 275223, "is_parallel": true, "self": 6.509174584930406, "children": { "process_trajectory": { "total": 283.97969094099426, "count": 275223, "is_parallel": true, "self": 283.4160108699948, "children": { "RLTrainer._checkpoint": { "total": 0.5636800709994532, "count": 4, "is_parallel": true, "self": 0.5636800709994532 } } }, "_update_policy": { "total": 213.52823750299876, "count": 90, "is_parallel": true, "self": 43.61161627900083, "children": { "TorchPPOOptimizer.update": { "total": 169.91662122399794, "count": 4587, "is_parallel": true, "self": 169.91662122399794 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08756281900014073, "count": 1, "self": 0.0009704190001684765, "children": { "RLTrainer._checkpoint": { "total": 0.08659239999997226, "count": 1, "self": 0.08659239999997226 } } } } } } }