{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8657838106155396, "min": 0.8631806969642639, "max": 2.861945867538452, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8266.50390625, "min": 8266.50390625, "max": 29309.1875, "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": 13.18843936920166, "min": 0.47114479541778564, "max": 13.244690895080566, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2571.74560546875, "min": 91.40209197998047, "max": 2710.56640625, "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": 0.06288786061582761, "min": 0.06288786061582761, "max": 0.074424361103664, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25155144246331046, "min": 0.25155144246331046, "max": 0.37212180551832, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20298739572000854, "min": 0.13529562027771116, "max": 0.2834278936771785, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8119495828800342, "min": 0.5411824811108447, "max": 1.4171394683858927, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.795454545454547, "min": 3.909090909090909, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1135.0, "min": 172.0, "max": 1436.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.795454545454547, "min": 3.909090909090909, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1135.0, "min": 172.0, "max": 1436.0, "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": "1712237538", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712238090" }, "total": 551.800650313, "count": 1, "self": 0.43362174399999276, "children": { "run_training.setup": { "total": 0.05539127399993049, "count": 1, "self": 0.05539127399993049 }, "TrainerController.start_learning": { "total": 551.3116372950001, "count": 1, "self": 0.6489777700082868, "children": { "TrainerController._reset_env": { "total": 3.0471148340000127, "count": 1, "self": 3.0471148340000127 }, "TrainerController.advance": { "total": 547.5249051479918, "count": 18199, "self": 0.3055861720044959, "children": { "env_step": { "total": 547.2193189759873, "count": 18199, "self": 385.51612531694855, "children": { "SubprocessEnvManager._take_step": { "total": 161.38237797004172, "count": 18199, "self": 1.5689270370482973, "children": { "TorchPolicy.evaluate": { "total": 159.81345093299342, "count": 18199, "self": 159.81345093299342 } } }, "workers": { "total": 0.32081568899707236, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 549.9648756769852, "count": 18199, "is_parallel": true, "self": 317.2415695599566, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006144939000023442, "count": 1, "is_parallel": true, "self": 0.00442741100027888, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017175279997445614, "count": 10, "is_parallel": true, "self": 0.0017175279997445614 } } }, "UnityEnvironment.step": { "total": 0.0369632450001518, "count": 1, "is_parallel": true, "self": 0.0006711130001804122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003906299998561735, "count": 1, "is_parallel": true, "self": 0.0003906299998561735 }, "communicator.exchange": { "total": 0.03396769400001176, "count": 1, "is_parallel": true, "self": 0.03396769400001176 }, "steps_from_proto": { "total": 0.001933808000103454, "count": 1, "is_parallel": true, "self": 0.0003964269994867209, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015373810006167332, "count": 10, "is_parallel": true, "self": 0.0015373810006167332 } } } } } } }, "UnityEnvironment.step": { "total": 232.72330611702864, "count": 18198, "is_parallel": true, "self": 10.646798499015404, "children": { "UnityEnvironment._generate_step_input": { "total": 5.615968260999352, "count": 18198, "is_parallel": true, "self": 5.615968260999352 }, "communicator.exchange": { "total": 181.92294891500842, "count": 18198, "is_parallel": true, "self": 181.92294891500842 }, "steps_from_proto": { "total": 34.53759044200547, "count": 18198, "is_parallel": true, "self": 6.683431574015003, "children": { "_process_rank_one_or_two_observation": { "total": 27.854158867990463, "count": 181980, "is_parallel": true, "self": 27.854158867990463 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001393029999690043, "count": 1, "self": 0.0001393029999690043, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 541.5429305959781, "count": 718159, "is_parallel": true, "self": 14.631519066006831, "children": { "process_trajectory": { "total": 250.00558710397104, "count": 718159, "is_parallel": true, "self": 249.2627079349711, "children": { "RLTrainer._checkpoint": { "total": 0.7428791689999343, "count": 4, "is_parallel": true, "self": 0.7428791689999343 } } }, "_update_policy": { "total": 276.9058244260002, "count": 90, "is_parallel": true, "self": 93.01811832198018, "children": { "TorchPPOOptimizer.update": { "total": 183.88770610402003, "count": 9174, "is_parallel": true, "self": 183.88770610402003 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09050023999998302, "count": 1, "self": 0.0010271619999002723, "children": { "RLTrainer._checkpoint": { "total": 0.08947307800008275, "count": 1, "self": 0.08947307800008275 } } } } } } }