{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8572671413421631, "min": 0.8572671413421631, "max": 2.8608365058898926, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8213.4765625, "min": 8213.4765625, "max": 29329.296875, "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": 12.157805442810059, "min": 0.23154209554195404, "max": 12.157805442810059, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2370.77197265625, "min": 44.919166564941406, "max": 2468.49755859375, "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": 0.06811576607031063, "min": 0.062360072770317465, "max": 0.07389505528090905, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2724630642812425, "min": 0.24944029108126986, "max": 0.36278725765930403, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2048699592842775, "min": 0.09718661300276461, "max": 0.28411044460885665, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.81947983713711, "min": 0.38874645201105845, "max": 1.4205522230442833, "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": 23.931818181818183, "min": 2.7954545454545454, "max": 24.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1053.0, "min": 123.0, "max": 1311.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.931818181818183, "min": 2.7954545454545454, "max": 24.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1053.0, "min": 123.0, "max": 1311.0, "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": "1734591509", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734592132" }, "total": 622.503094153, "count": 1, "self": 0.540212428000018, "children": { "run_training.setup": { "total": 0.09704434100001436, "count": 1, "self": 0.09704434100001436 }, "TrainerController.start_learning": { "total": 621.865837384, "count": 1, "self": 0.9657371149967275, "children": { "TrainerController._reset_env": { "total": 10.256565346000002, "count": 1, "self": 10.256565346000002 }, "TrainerController.advance": { "total": 610.5484756550031, "count": 18204, "self": 0.4547215670066862, "children": { "env_step": { "total": 610.0937540879964, "count": 18204, "self": 468.5233814149682, "children": { "SubprocessEnvManager._take_step": { "total": 141.13562870000862, "count": 18204, "self": 2.7614599500016084, "children": { "TorchPolicy.evaluate": { "total": 138.37416875000702, "count": 18204, "self": 138.37416875000702 } } }, "workers": { "total": 0.43474397301963563, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 619.8550303890115, "count": 18204, "is_parallel": true, "self": 300.18286398599616, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003869165999958568, "count": 1, "is_parallel": true, "self": 0.0012349009999752525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026342649999833156, "count": 10, "is_parallel": true, "self": 0.0026342649999833156 } } }, "UnityEnvironment.step": { "total": 0.10889808899992204, "count": 1, "is_parallel": true, "self": 0.0017551289998891662, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0011965879999706885, "count": 1, "is_parallel": true, "self": 0.0011965879999706885 }, "communicator.exchange": { "total": 0.10038432500005001, "count": 1, "is_parallel": true, "self": 0.10038432500005001 }, "steps_from_proto": { "total": 0.005562047000012171, "count": 1, "is_parallel": true, "self": 0.0009736470001371345, "children": { "_process_rank_one_or_two_observation": { "total": 0.004588399999875037, "count": 10, "is_parallel": true, "self": 0.004588399999875037 } } } } } } }, "UnityEnvironment.step": { "total": 319.67216640301535, "count": 18203, "is_parallel": true, "self": 15.312327775995755, "children": { "UnityEnvironment._generate_step_input": { "total": 7.642080377994148, "count": 18203, "is_parallel": true, "self": 7.642080377994148 }, "communicator.exchange": { "total": 251.11901144301794, "count": 18203, "is_parallel": true, "self": 251.11901144301794 }, "steps_from_proto": { "total": 45.59874680600751, "count": 18203, "is_parallel": true, "self": 9.026811958031885, "children": { "_process_rank_one_or_two_observation": { "total": 36.571934847975626, "count": 182030, "is_parallel": true, "self": 36.571934847975626 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00025816500010478194, "count": 1, "self": 0.00025816500010478194, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 603.1113343080269, "count": 772206, "is_parallel": true, "self": 18.666106614989076, "children": { "process_trajectory": { "total": 326.9477105080382, "count": 772206, "is_parallel": true, "self": 325.60788937003815, "children": { "RLTrainer._checkpoint": { "total": 1.3398211380000475, "count": 4, "is_parallel": true, "self": 1.3398211380000475 } } }, "_update_policy": { "total": 257.49751718499965, "count": 90, "is_parallel": true, "self": 72.17253183100206, "children": { "TorchPPOOptimizer.update": { "total": 185.3249853539976, "count": 4587, "is_parallel": true, "self": 185.3249853539976 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09480110300000888, "count": 1, "self": 0.0013258040000891924, "children": { "RLTrainer._checkpoint": { "total": 0.09347529899991969, "count": 1, "self": 0.09347529899991969 } } } } } } }