{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8333675265312195, "min": 0.8333675265312195, "max": 2.835420846939087, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7920.3251953125, "min": 7920.3251953125, "max": 28943.9765625, "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": 12.83678913116455, "min": 0.24047231674194336, "max": 12.83678913116455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2503.173828125, "min": 46.65163040161133, "max": 2576.27587890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06915126292077213, "min": 0.06446432931127265, "max": 0.07450675642358678, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2766050516830885, "min": 0.26015425430823064, "max": 0.37235157737421676, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1925397295066539, "min": 0.13175424232658947, "max": 0.2857211517937043, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7701589180266156, "min": 0.5270169693063579, "max": 1.4286057589685215, "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": 25.90909090909091, "min": 3.6363636363636362, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 160.0, "max": 1366.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.6363636363636362, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 160.0, "max": 1366.0, "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": "1740608178", "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": "1740608594" }, "total": 415.95315523600004, "count": 1, "self": 0.4367512730001408, "children": { "run_training.setup": { "total": 0.02323760499996297, "count": 1, "self": 0.02323760499996297 }, "TrainerController.start_learning": { "total": 415.49316635799994, "count": 1, "self": 0.3318550840037915, "children": { "TrainerController._reset_env": { "total": 3.0499124800001027, "count": 1, "self": 3.0499124800001027 }, "TrainerController.advance": { "total": 412.0228691519959, "count": 18192, "self": 0.3293964380000034, "children": { "env_step": { "total": 290.30010519600717, "count": 18192, "self": 220.68320927801767, "children": { "SubprocessEnvManager._take_step": { "total": 69.42120016399167, "count": 18192, "self": 1.2144842960013875, "children": { "TorchPolicy.evaluate": { "total": 68.20671586799028, "count": 18192, "self": 68.20671586799028 } } }, "workers": { "total": 0.1956957539978248, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 414.01681157200244, "count": 18192, "is_parallel": true, "self": 220.64144244599947, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005582768000067517, "count": 1, "is_parallel": true, "self": 0.004035963999854175, "children": { "_process_rank_one_or_two_observation": { "total": 0.001546804000213342, "count": 10, "is_parallel": true, "self": 0.001546804000213342 } } }, "UnityEnvironment.step": { "total": 0.037723528000014994, "count": 1, "is_parallel": true, "self": 0.0005648329999985435, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037746900000001915, "count": 1, "is_parallel": true, "self": 0.00037746900000001915 }, "communicator.exchange": { "total": 0.03490941000006842, "count": 1, "is_parallel": true, "self": 0.03490941000006842 }, "steps_from_proto": { "total": 0.0018718159999480122, "count": 1, "is_parallel": true, "self": 0.0003629339998951764, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015088820000528358, "count": 10, "is_parallel": true, "self": 0.0015088820000528358 } } } } } } }, "UnityEnvironment.step": { "total": 193.37536912600297, "count": 18191, "is_parallel": true, "self": 9.447781897003551, "children": { "UnityEnvironment._generate_step_input": { "total": 5.249895053000273, "count": 18191, "is_parallel": true, "self": 5.249895053000273 }, "communicator.exchange": { "total": 148.41962037300027, "count": 18191, "is_parallel": true, "self": 148.41962037300027 }, "steps_from_proto": { "total": 30.25807180299887, "count": 18191, "is_parallel": true, "self": 5.2814428259898705, "children": { "_process_rank_one_or_two_observation": { "total": 24.976628977009, "count": 181910, "is_parallel": true, "self": 24.976628977009 } } } } } } } } } } }, "trainer_advance": { "total": 121.39336751798874, "count": 18192, "self": 0.39914997498442517, "children": { "process_trajectory": { "total": 26.36028267200618, "count": 18192, "self": 25.769819393005946, "children": { "RLTrainer._checkpoint": { "total": 0.5904632790002324, "count": 4, "self": 0.5904632790002324 } } }, "_update_policy": { "total": 94.63393487099813, "count": 90, "self": 37.78909191599155, "children": { "TorchPPOOptimizer.update": { "total": 56.844842955006584, "count": 4587, "self": 56.844842955006584 } } } } } } }, "trainer_threads": { "total": 1.2650000371650094e-06, "count": 1, "self": 1.2650000371650094e-06 }, "TrainerController._save_models": { "total": 0.08852837700010241, "count": 1, "self": 0.0008865770000738848, "children": { "RLTrainer._checkpoint": { "total": 0.08764180000002852, "count": 1, "self": 0.08764180000002852 } } } } } } }