{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8663073778152466, "min": 0.8663073778152466, "max": 2.8803491592407227, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8281.0322265625, "min": 8281.0322265625, "max": 29529.33984375, "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": 13.074111938476562, "min": 0.13339874148368835, "max": 13.074111938476562, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2549.451904296875, "min": 25.879356384277344, "max": 2630.240234375, "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": 0.07072148541452657, "min": 0.06373000428874923, "max": 0.07335336173584403, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28288594165810627, "min": 0.2672008319956398, "max": 0.36209047654348053, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1815636157989502, "min": 0.08521692833963636, "max": 0.29270752680067924, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7262544631958008, "min": 0.34086771335854543, "max": 1.463537634003396, "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": 25.772727272727273, "min": 2.3181818181818183, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 102.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 2.3181818181818183, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 102.0, "max": 1393.0, "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": "1691799796", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691800304" }, "total": 507.10456180600005, "count": 1, "self": 0.4353784030000156, "children": { "run_training.setup": { "total": 0.045735336999996434, "count": 1, "self": 0.045735336999996434 }, "TrainerController.start_learning": { "total": 506.62344806600004, "count": 1, "self": 0.5878243200046427, "children": { "TrainerController._reset_env": { "total": 4.345333832999984, "count": 1, "self": 4.345333832999984 }, "TrainerController.advance": { "total": 501.5462641979954, "count": 18203, "self": 0.2942748779936437, "children": { "env_step": { "total": 501.25198932000177, "count": 18203, "self": 367.5750083460017, "children": { "SubprocessEnvManager._take_step": { "total": 133.38173503400702, "count": 18203, "self": 1.9403090200104884, "children": { "TorchPolicy.evaluate": { "total": 131.44142601399653, "count": 18203, "self": 131.44142601399653 } } }, "workers": { "total": 0.2952459399930376, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 504.73829748400533, "count": 18203, "is_parallel": true, "self": 237.94712023799497, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005963253000004443, "count": 1, "is_parallel": true, "self": 0.004385282999976425, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015779700000280172, "count": 10, "is_parallel": true, "self": 0.0015779700000280172 } } }, "UnityEnvironment.step": { "total": 0.06843506900003149, "count": 1, "is_parallel": true, "self": 0.0007106119999775729, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003460370000425428, "count": 1, "is_parallel": true, "self": 0.0003460370000425428 }, "communicator.exchange": { "total": 0.05837926700002072, "count": 1, "is_parallel": true, "self": 0.05837926700002072 }, "steps_from_proto": { "total": 0.008999152999990656, "count": 1, "is_parallel": true, "self": 0.0004496929999504573, "children": { "_process_rank_one_or_two_observation": { "total": 0.008549460000040199, "count": 10, "is_parallel": true, "self": 0.008549460000040199 } } } } } } }, "UnityEnvironment.step": { "total": 266.79117724601036, "count": 18202, "is_parallel": true, "self": 11.248890281002673, "children": { "UnityEnvironment._generate_step_input": { "total": 5.552173533996211, "count": 18202, "is_parallel": true, "self": 5.552173533996211 }, "communicator.exchange": { "total": 211.20265713500135, "count": 18202, "is_parallel": true, "self": 211.20265713500135 }, "steps_from_proto": { "total": 38.787456296010134, "count": 18202, "is_parallel": true, "self": 7.127805943024555, "children": { "_process_rank_one_or_two_observation": { "total": 31.65965035298558, "count": 182020, "is_parallel": true, "self": 31.65965035298558 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015973500001109642, "count": 1, "self": 0.00015973500001109642, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 497.45336423899266, "count": 468740, "is_parallel": true, "self": 10.86786894597708, "children": { "process_trajectory": { "total": 270.69915334601603, "count": 468740, "is_parallel": true, "self": 269.4920891290162, "children": { "RLTrainer._checkpoint": { "total": 1.207064216999811, "count": 4, "is_parallel": true, "self": 1.207064216999811 } } }, "_update_policy": { "total": 215.88634194699955, "count": 90, "is_parallel": true, "self": 88.15543634800247, "children": { "TorchPPOOptimizer.update": { "total": 127.73090559899708, "count": 4587, "is_parallel": true, "self": 127.73090559899708 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14386597999998685, "count": 1, "self": 0.0009130869999580682, "children": { "RLTrainer._checkpoint": { "total": 0.14295289300002878, "count": 1, "self": 0.14295289300002878 } } } } } } }