{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9578738212585449, "min": 0.9578738212585449, "max": 2.8568689823150635, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9145.779296875, "min": 9145.779296875, "max": 29225.76953125, "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": 13.451546669006348, "min": 0.39866381883621216, "max": 13.451546669006348, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2623.051513671875, "min": 77.34078216552734, "max": 2737.64794921875, "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": 0.06245335479059791, "min": 0.062019714214222726, "max": 0.07422365628252223, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24981341916239164, "min": 0.2480788568568909, "max": 0.37111828141261116, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20716308780452783, "min": 0.12333254989318768, "max": 0.2972742574764233, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8286523512181113, "min": 0.4933301995727507, "max": 1.3786861735816094, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600007e-05, "min": 8.082009730600007e-05, "max": 0.0029188200027059994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00032328038922400026, "min": 0.00032328038922400026, "max": 0.013851600038280001, "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": 26.272727272727273, "min": 3.25, "max": 26.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1156.0, "min": 143.0, "max": 1476.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.272727272727273, "min": 3.25, "max": 26.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1156.0, "min": 143.0, "max": 1476.0, "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": "1677674021", "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 ./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": "1.22.4", "end_time_seconds": "1677674461" }, "total": 439.07544767800005, "count": 1, "self": 0.38603841400026795, "children": { "run_training.setup": { "total": 0.11252203599997301, "count": 1, "self": 0.11252203599997301 }, "TrainerController.start_learning": { "total": 438.5768872279998, "count": 1, "self": 0.49461877801877563, "children": { "TrainerController._reset_env": { "total": 9.245061680999925, "count": 1, "self": 9.245061680999925 }, "TrainerController.advance": { "total": 428.7236573469811, "count": 18201, "self": 0.26300936399206876, "children": { "env_step": { "total": 428.46064798298903, "count": 18201, "self": 292.56274978300826, "children": { "SubprocessEnvManager._take_step": { "total": 135.63779164099378, "count": 18201, "self": 1.451497099001699, "children": { "TorchPolicy.evaluate": { "total": 134.18629454199208, "count": 18201, "self": 29.77742390400067, "children": { "TorchPolicy.sample_actions": { "total": 104.40887063799141, "count": 18201, "self": 104.40887063799141 } } } } }, "workers": { "total": 0.2601065589869904, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 437.1467099460008, "count": 18201, "is_parallel": true, "self": 212.7757966210238, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005505972000037218, "count": 1, "is_parallel": true, "self": 0.004242626999939603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012633450000976154, "count": 10, "is_parallel": true, "self": 0.0012633450000976154 } } }, "UnityEnvironment.step": { "total": 0.04531355899985101, "count": 1, "is_parallel": true, "self": 0.0004432159996667906, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037771899997096625, "count": 1, "is_parallel": true, "self": 0.00037771899997096625 }, "communicator.exchange": { "total": 0.04270592900002157, "count": 1, "is_parallel": true, "self": 0.04270592900002157 }, "steps_from_proto": { "total": 0.0017866950001916848, "count": 1, "is_parallel": true, "self": 0.0004104499998902611, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013762450003014237, "count": 10, "is_parallel": true, "self": 0.0013762450003014237 } } } } } } }, "UnityEnvironment.step": { "total": 224.37091332497698, "count": 18200, "is_parallel": true, "self": 9.217192471967564, "children": { "UnityEnvironment._generate_step_input": { "total": 4.954859627020596, "count": 18200, "is_parallel": true, "self": 4.954859627020596 }, "communicator.exchange": { "total": 180.68220747698774, "count": 18200, "is_parallel": true, "self": 180.68220747698774 }, "steps_from_proto": { "total": 29.51665374900108, "count": 18200, "is_parallel": true, "self": 6.416180842037875, "children": { "_process_rank_one_or_two_observation": { "total": 23.100472906963205, "count": 182000, "is_parallel": true, "self": 23.100472906963205 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014432800003305601, "count": 1, "self": 0.00014432800003305601, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 425.6807832149566, "count": 390670, "is_parallel": true, "self": 9.611744609871039, "children": { "process_trajectory": { "total": 243.60945927908438, "count": 390670, "is_parallel": true, "self": 242.56619191408458, "children": { "RLTrainer._checkpoint": { "total": 1.0432673649997923, "count": 4, "is_parallel": true, "self": 1.0432673649997923 } } }, "_update_policy": { "total": 172.45957932600118, "count": 90, "is_parallel": true, "self": 58.83220705401777, "children": { "TorchPPOOptimizer.update": { "total": 113.6273722719834, "count": 4584, "is_parallel": true, "self": 113.6273722719834 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11340509399997245, "count": 1, "self": 0.0008426000001691136, "children": { "RLTrainer._checkpoint": { "total": 0.11256249399980334, "count": 1, "self": 0.11256249399980334 } } } } } } }