{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9433902502059937, "min": 0.9433902502059937, "max": 2.859973669052124, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9007.490234375, "min": 9007.490234375, "max": 29288.990234375, "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": 12.8394193649292, "min": 0.4369000792503357, "max": 12.8394193649292, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2503.686767578125, "min": 84.75861358642578, "max": 2606.0068359375, "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": 0.06741483299422316, "min": 0.06184676985957434, "max": 0.07980881659336864, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2696593319768926, "min": 0.2674881041042253, "max": 0.3670451788961609, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.209397202613307, "min": 0.11605154936984821, "max": 0.2806769926466194, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.837588810453228, "min": 0.46420619747939285, "max": 1.3476857963730309, "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": 25.25, "min": 3.409090909090909, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 150.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.409090909090909, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 150.0, "max": 1386.0, "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": "1674414153", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674414590" }, "total": 436.775219438, "count": 1, "self": 0.3910607340000638, "children": { "run_training.setup": { "total": 0.12333285500000102, "count": 1, "self": 0.12333285500000102 }, "TrainerController.start_learning": { "total": 436.26082584899996, "count": 1, "self": 0.5250637720090481, "children": { "TrainerController._reset_env": { "total": 9.31975363700002, "count": 1, "self": 9.31975363700002 }, "TrainerController.advance": { "total": 426.29191515099086, "count": 18203, "self": 0.26581534499752024, "children": { "env_step": { "total": 426.02609980599334, "count": 18203, "self": 275.7374435539842, "children": { "SubprocessEnvManager._take_step": { "total": 150.022489465008, "count": 18203, "self": 1.420615935007163, "children": { "TorchPolicy.evaluate": { "total": 148.60187353000083, "count": 18203, "self": 33.729499033994614, "children": { "TorchPolicy.sample_actions": { "total": 114.87237449600622, "count": 18203, "self": 114.87237449600622 } } } } }, "workers": { "total": 0.26616678700116836, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 435.0300448499971, "count": 18203, "is_parallel": true, "self": 211.55189190799513, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005654199999980847, "count": 1, "is_parallel": true, "self": 0.003369094000106543, "children": { "_process_rank_one_or_two_observation": { "total": 0.002285105999874304, "count": 10, "is_parallel": true, "self": 0.002285105999874304 } } }, "UnityEnvironment.step": { "total": 0.038792546000024686, "count": 1, "is_parallel": true, "self": 0.0005245030000082807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000344211000026462, "count": 1, "is_parallel": true, "self": 0.000344211000026462 }, "communicator.exchange": { "total": 0.03611391499998717, "count": 1, "is_parallel": true, "self": 0.03611391499998717 }, "steps_from_proto": { "total": 0.0018099170000027698, "count": 1, "is_parallel": true, "self": 0.000438416999884339, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013715000001184308, "count": 10, "is_parallel": true, "self": 0.0013715000001184308 } } } } } } }, "UnityEnvironment.step": { "total": 223.478152942002, "count": 18202, "is_parallel": true, "self": 8.46519830399302, "children": { "UnityEnvironment._generate_step_input": { "total": 5.190888459006658, "count": 18202, "is_parallel": true, "self": 5.190888459006658 }, "communicator.exchange": { "total": 178.44701770000495, "count": 18202, "is_parallel": true, "self": 178.44701770000495 }, "steps_from_proto": { "total": 31.37504847899737, "count": 18202, "is_parallel": true, "self": 6.670994370006554, "children": { "_process_rank_one_or_two_observation": { "total": 24.704054108990817, "count": 182020, "is_parallel": true, "self": 24.704054108990817 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.9775000004738104e-05, "count": 1, "self": 3.9775000004738104e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 423.0582089980365, "count": 342680, "is_parallel": true, "self": 9.724690289011562, "children": { "process_trajectory": { "total": 243.00185648702558, "count": 342680, "is_parallel": true, "self": 242.22279692502565, "children": { "RLTrainer._checkpoint": { "total": 0.7790595619999294, "count": 4, "is_parallel": true, "self": 0.7790595619999294 } } }, "_update_policy": { "total": 170.33166222199935, "count": 90, "is_parallel": true, "self": 42.110309222998694, "children": { "TorchPPOOptimizer.update": { "total": 128.22135299900066, "count": 4584, "is_parallel": true, "self": 128.22135299900066 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12405351400002473, "count": 1, "self": 0.0008972929999799817, "children": { "RLTrainer._checkpoint": { "total": 0.12315622100004475, "count": 1, "self": 0.12315622100004475 } } } } } } }