{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8473865389823914, "min": 0.8435367941856384, "max": 2.8283541202545166, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8053.5615234375, "min": 8053.5615234375, "max": 28871.83984375, "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": 12.871747016906738, "min": 0.23091088235378265, "max": 12.871747016906738, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2509.99072265625, "min": 44.79671096801758, "max": 2627.80224609375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0698169857511554, "min": 0.06322084568262867, "max": 0.07713356549042966, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2792679430046216, "min": 0.2528833827305147, "max": 0.3800664860275848, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18894887861667894, "min": 0.13818919774391414, "max": 0.2634664147215731, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7557955144667158, "min": 0.5527567909756566, "max": 1.274626416026377, "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.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.Environment.CumulativeReward.mean": { "value": 25.431818181818183, "min": 3.6818181818181817, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 162.0, "max": 1409.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.6818181818181817, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 162.0, "max": 1409.0, "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": "1741951126", "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 --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741951568" }, "total": 442.53979727600006, "count": 1, "self": 0.4353333360000988, "children": { "run_training.setup": { "total": 0.034603981999907774, "count": 1, "self": 0.034603981999907774 }, "TrainerController.start_learning": { "total": 442.06985995800005, "count": 1, "self": 0.3450776259885515, "children": { "TrainerController._reset_env": { "total": 3.4210789530000056, "count": 1, "self": 3.4210789530000056 }, "TrainerController.advance": { "total": 438.21466827901145, "count": 18192, "self": 0.36239359802198123, "children": { "env_step": { "total": 313.0023271269963, "count": 18192, "self": 237.34498498503797, "children": { "SubprocessEnvManager._take_step": { "total": 75.44203250797659, "count": 18192, "self": 1.3084723809856769, "children": { "TorchPolicy.evaluate": { "total": 74.13356012699091, "count": 18192, "self": 74.13356012699091 } } }, "workers": { "total": 0.21530963398174663, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 440.638795214001, "count": 18192, "is_parallel": true, "self": 232.26954801999068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0069237280000606916, "count": 1, "is_parallel": true, "self": 0.004806181000049037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021175470000116547, "count": 10, "is_parallel": true, "self": 0.0021175470000116547 } } }, "UnityEnvironment.step": { "total": 0.03932153300002028, "count": 1, "is_parallel": true, "self": 0.0006396410000206743, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040385499994499696, "count": 1, "is_parallel": true, "self": 0.00040385499994499696 }, "communicator.exchange": { "total": 0.03638748400010172, "count": 1, "is_parallel": true, "self": 0.03638748400010172 }, "steps_from_proto": { "total": 0.001890552999952888, "count": 1, "is_parallel": true, "self": 0.000378445000251304, "children": { "_process_rank_one_or_two_observation": { "total": 0.001512107999701584, "count": 10, "is_parallel": true, "self": 0.001512107999701584 } } } } } } }, "UnityEnvironment.step": { "total": 208.3692471940103, "count": 18191, "is_parallel": true, "self": 9.998856494014717, "children": { "UnityEnvironment._generate_step_input": { "total": 5.601471742990157, "count": 18191, "is_parallel": true, "self": 5.601471742990157 }, "communicator.exchange": { "total": 159.6552463519963, "count": 18191, "is_parallel": true, "self": 159.6552463519963 }, "steps_from_proto": { "total": 33.11367260500913, "count": 18191, "is_parallel": true, "self": 5.905163163016823, "children": { "_process_rank_one_or_two_observation": { "total": 27.208509441992305, "count": 181910, "is_parallel": true, "self": 27.208509441992305 } } } } } } } } } } }, "trainer_advance": { "total": 124.84994755399316, "count": 18192, "self": 0.42086420899454424, "children": { "process_trajectory": { "total": 27.90155592199858, "count": 18192, "self": 27.4669253719984, "children": { "RLTrainer._checkpoint": { "total": 0.43463055000017903, "count": 4, "self": 0.43463055000017903 } } }, "_update_policy": { "total": 96.52752742300004, "count": 90, "self": 38.59211910900524, "children": { "TorchPPOOptimizer.update": { "total": 57.9354083139948, "count": 4587, "self": 57.9354083139948 } } } } } } }, "trainer_threads": { "total": 1.0129999736818718e-06, "count": 1, "self": 1.0129999736818718e-06 }, "TrainerController._save_models": { "total": 0.08903408700007276, "count": 1, "self": 0.0009712290000152279, "children": { "RLTrainer._checkpoint": { "total": 0.08806285800005753, "count": 1, "self": 0.08806285800005753 } } } } } } }