{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9546141028404236, "min": 0.9546141028404236, "max": 2.8449180126190186, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9114.6552734375, "min": 9114.6552734375, "max": 29134.8046875, "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": 11.942099571228027, "min": 0.4216964542865753, "max": 11.942099571228027, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2328.70947265625, "min": 81.80911254882812, "max": 2409.496826171875, "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": 0.06798278137427463, "min": 0.06469691636876257, "max": 0.07426519850688397, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2719311254970985, "min": 0.2587876654750503, "max": 0.36021284786778884, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19951574007670084, "min": 0.13851575306205846, "max": 0.27990009673670224, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7980629603068033, "min": 0.5540630122482338, "max": 1.3995004836835112, "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": 23.977272727272727, "min": 3.522727272727273, "max": 23.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1055.0, "min": 155.0, "max": 1279.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.977272727272727, "min": 3.522727272727273, "max": 23.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1055.0, "min": 155.0, "max": 1279.0, "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": "1709189344", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709189813" }, "total": 468.9700024499998, "count": 1, "self": 0.44210875399949146, "children": { "run_training.setup": { "total": 0.04544431800059101, "count": 1, "self": 0.04544431800059101 }, "TrainerController.start_learning": { "total": 468.4824493779997, "count": 1, "self": 0.5827746090462824, "children": { "TrainerController._reset_env": { "total": 2.1861548830001993, "count": 1, "self": 2.1861548830001993 }, "TrainerController.advance": { "total": 465.6201342809527, "count": 18200, "self": 0.2883062078944931, "children": { "env_step": { "total": 465.3318280730582, "count": 18200, "self": 301.24688933515245, "children": { "SubprocessEnvManager._take_step": { "total": 163.78369763700448, "count": 18200, "self": 1.564372793003713, "children": { "TorchPolicy.evaluate": { "total": 162.21932484400077, "count": 18200, "self": 162.21932484400077 } } }, "workers": { "total": 0.3012411009012794, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 467.1852629820487, "count": 18200, "is_parallel": true, "self": 230.50144642317264, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023687490001975675, "count": 1, "is_parallel": true, "self": 0.0007358200027738349, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016329289974237327, "count": 10, "is_parallel": true, "self": 0.0016329289974237327 } } }, "UnityEnvironment.step": { "total": 0.03941695100002107, "count": 1, "is_parallel": true, "self": 0.0006506749996333383, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004001440001957235, "count": 1, "is_parallel": true, "self": 0.0004001440001957235 }, "communicator.exchange": { "total": 0.03644739900028071, "count": 1, "is_parallel": true, "self": 0.03644739900028071 }, "steps_from_proto": { "total": 0.001918732999911299, "count": 1, "is_parallel": true, "self": 0.0003886260001308983, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015301069997804007, "count": 10, "is_parallel": true, "self": 0.0015301069997804007 } } } } } } }, "UnityEnvironment.step": { "total": 236.68381655887606, "count": 18199, "is_parallel": true, "self": 11.189358309766249, "children": { "UnityEnvironment._generate_step_input": { "total": 5.80749829899014, "count": 18199, "is_parallel": true, "self": 5.80749829899014 }, "communicator.exchange": { "total": 182.91339907005204, "count": 18199, "is_parallel": true, "self": 182.91339907005204 }, "steps_from_proto": { "total": 36.773560880067635, "count": 18199, "is_parallel": true, "self": 6.847737565098214, "children": { "_process_rank_one_or_two_observation": { "total": 29.92582331496942, "count": 181990, "is_parallel": true, "self": 29.92582331496942 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013166300050215796, "count": 1, "self": 0.00013166300050215796, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 459.55956797392537, "count": 687612, "is_parallel": true, "self": 15.373373817905303, "children": { "process_trajectory": { "total": 254.12298697402093, "count": 687612, "is_parallel": true, "self": 253.24456514902067, "children": { "RLTrainer._checkpoint": { "total": 0.8784218250002596, "count": 4, "is_parallel": true, "self": 0.8784218250002596 } } }, "_update_policy": { "total": 190.06320718199913, "count": 90, "is_parallel": true, "self": 53.01704609301396, "children": { "TorchPPOOptimizer.update": { "total": 137.04616108898517, "count": 4584, "is_parallel": true, "self": 137.04616108898517 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09325394200004666, "count": 1, "self": 0.00100795999969705, "children": { "RLTrainer._checkpoint": { "total": 0.09224598200034961, "count": 1, "self": 0.09224598200034961 } } } } } } }