{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0006742477416992, "min": 1.0006742477416992, "max": 2.8659210205078125, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9554.4375, "min": 9554.4375, "max": 29381.421875, "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": 12.567713737487793, "min": 0.38466447591781616, "max": 12.567713737487793, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2450.7041015625, "min": 74.62490844726562, "max": 2533.6982421875, "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": 0.06775474859008968, "min": 0.06289641794983433, "max": 0.07432345583488224, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2710189943603587, "min": 0.26051240516872165, "max": 0.37161727917441123, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1975701829674197, "min": 0.12026640623305723, "max": 0.2932920032856511, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7902807318696788, "min": 0.48106562493222893, "max": 1.4664600164282555, "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": 24.977272727272727, "min": 3.3181818181818183, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 146.0, "max": 1353.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.3181818181818183, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 146.0, "max": 1353.0, "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": "1678985289", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678985748" }, "total": 458.461173326, "count": 1, "self": 0.4278694219999579, "children": { "run_training.setup": { "total": 0.10860596500000952, "count": 1, "self": 0.10860596500000952 }, "TrainerController.start_learning": { "total": 457.92469793900005, "count": 1, "self": 0.5454323040013378, "children": { "TrainerController._reset_env": { "total": 9.369324665000022, "count": 1, "self": 9.369324665000022 }, "TrainerController.advance": { "total": 447.8787338629987, "count": 18201, "self": 0.2808378079914178, "children": { "env_step": { "total": 447.59789605500725, "count": 18201, "self": 324.1301853760099, "children": { "SubprocessEnvManager._take_step": { "total": 123.20400422200365, "count": 18201, "self": 2.0306372500032808, "children": { "TorchPolicy.evaluate": { "total": 121.17336697200037, "count": 18201, "self": 121.17336697200037 } } }, "workers": { "total": 0.2637064569937593, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 456.52092677299925, "count": 18201, "is_parallel": true, "self": 217.6389669730009, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005976062999991427, "count": 1, "is_parallel": true, "self": 0.004442185000016252, "children": { "_process_rank_one_or_two_observation": { "total": 0.001533877999975175, "count": 10, "is_parallel": true, "self": 0.001533877999975175 } } }, "UnityEnvironment.step": { "total": 0.10477444100001776, "count": 1, "is_parallel": true, "self": 0.006530690999994704, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045363500001371904, "count": 1, "is_parallel": true, "self": 0.00045363500001371904 }, "communicator.exchange": { "total": 0.09050651399999765, "count": 1, "is_parallel": true, "self": 0.09050651399999765 }, "steps_from_proto": { "total": 0.007283601000011686, "count": 1, "is_parallel": true, "self": 0.0003864870000143128, "children": { "_process_rank_one_or_two_observation": { "total": 0.006897113999997373, "count": 10, "is_parallel": true, "self": 0.006897113999997373 } } } } } } }, "UnityEnvironment.step": { "total": 238.88195979999836, "count": 18200, "is_parallel": true, "self": 9.570402731990612, "children": { "UnityEnvironment._generate_step_input": { "total": 5.103622965006878, "count": 18200, "is_parallel": true, "self": 5.103622965006878 }, "communicator.exchange": { "total": 193.73055856699838, "count": 18200, "is_parallel": true, "self": 193.73055856699838 }, "steps_from_proto": { "total": 30.477375536002484, "count": 18200, "is_parallel": true, "self": 6.032038180009039, "children": { "_process_rank_one_or_two_observation": { "total": 24.445337355993445, "count": 182000, "is_parallel": true, "self": 24.445337355993445 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001157409999450465, "count": 1, "self": 0.0001157409999450465, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.78629745999166, "count": 392109, "is_parallel": true, "self": 9.240268402990125, "children": { "process_trajectory": { "total": 244.3337443390014, "count": 392109, "is_parallel": true, "self": 243.60354508400135, "children": { "RLTrainer._checkpoint": { "total": 0.7301992550000591, "count": 4, "is_parallel": true, "self": 0.7301992550000591 } } }, "_update_policy": { "total": 191.21228471800012, "count": 90, "is_parallel": true, "self": 73.44514242400163, "children": { "TorchPPOOptimizer.update": { "total": 117.76714229399849, "count": 4587, "is_parallel": true, "self": 117.76714229399849 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13109136600007787, "count": 1, "self": 0.0008577900000545924, "children": { "RLTrainer._checkpoint": { "total": 0.13023357600002328, "count": 1, "self": 0.13023357600002328 } } } } } } }