{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9851040840148926, "min": 0.9830117225646973, "max": 2.848501205444336, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9449.1181640625, "min": 9449.1181640625, "max": 29265.501953125, "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": 10.997976303100586, "min": 0.2855055630207062, "max": 10.997976303100586, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2144.60546875, "min": 55.38808059692383, "max": 2228.625244140625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.062158868429975755, "min": 0.06016738360471494, "max": 0.07631203894924707, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24863547371990302, "min": 0.24863547371990302, "max": 0.3815601947462353, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20510813739954256, "min": 0.1191740299177849, "max": 0.2947825833862903, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8204325495981702, "min": 0.4766961196711396, "max": 1.4739129169314515, "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": 21.954545454545453, "min": 3.1818181818181817, "max": 21.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 966.0, "min": 140.0, "max": 1169.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.954545454545453, "min": 3.1818181818181817, "max": 21.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 966.0, "min": 140.0, "max": 1169.0, "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": "1695837354", "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": "1695837735" }, "total": 381.1709784950001, "count": 1, "self": 0.2767088169998715, "children": { "run_training.setup": { "total": 0.039207767000107197, "count": 1, "self": 0.039207767000107197 }, "TrainerController.start_learning": { "total": 380.8550619110001, "count": 1, "self": 0.5241088260129345, "children": { "TrainerController._reset_env": { "total": 4.0332117550001385, "count": 1, "self": 4.0332117550001385 }, "TrainerController.advance": { "total": 376.1646538849873, "count": 18205, "self": 0.24963996800988753, "children": { "env_step": { "total": 375.9150139169774, "count": 18205, "self": 273.03117404598265, "children": { "SubprocessEnvManager._take_step": { "total": 102.64289611999425, "count": 18205, "self": 1.3163880399908976, "children": { "TorchPolicy.evaluate": { "total": 101.32650808000335, "count": 18205, "self": 101.32650808000335 } } }, "workers": { "total": 0.24094375100048637, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 380.060407134014, "count": 18205, "is_parallel": true, "self": 188.5617459459877, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001978699999881428, "count": 1, "is_parallel": true, "self": 0.0005963190001239127, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013823809997575154, "count": 10, "is_parallel": true, "self": 0.0013823809997575154 } } }, "UnityEnvironment.step": { "total": 0.03228663499999129, "count": 1, "is_parallel": true, "self": 0.0006891000000450731, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003966809999838006, "count": 1, "is_parallel": true, "self": 0.0003966809999838006 }, "communicator.exchange": { "total": 0.02801766199991107, "count": 1, "is_parallel": true, "self": 0.02801766199991107 }, "steps_from_proto": { "total": 0.003183192000051349, "count": 1, "is_parallel": true, "self": 0.0004205429993362486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027626490007151006, "count": 10, "is_parallel": true, "self": 0.0027626490007151006 } } } } } } }, "UnityEnvironment.step": { "total": 191.4986611880263, "count": 18204, "is_parallel": true, "self": 7.66024153001581, "children": { "UnityEnvironment._generate_step_input": { "total": 4.015317608001624, "count": 18204, "is_parallel": true, "self": 4.015317608001624 }, "communicator.exchange": { "total": 154.14967022701194, "count": 18204, "is_parallel": true, "self": 154.14967022701194 }, "steps_from_proto": { "total": 25.673431822996918, "count": 18204, "is_parallel": true, "self": 4.7292468080174785, "children": { "_process_rank_one_or_two_observation": { "total": 20.94418501497944, "count": 182040, "is_parallel": true, "self": 20.94418501497944 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001380469998366607, "count": 1, "self": 0.0001380469998366607, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 374.9507946399908, "count": 236654, "is_parallel": true, "self": 4.211027802019089, "children": { "process_trajectory": { "total": 207.89769513097258, "count": 236654, "is_parallel": true, "self": 207.1374178719725, "children": { "RLTrainer._checkpoint": { "total": 0.7602772590000768, "count": 4, "is_parallel": true, "self": 0.7602772590000768 } } }, "_update_policy": { "total": 162.84207170699915, "count": 90, "is_parallel": true, "self": 44.49710333700614, "children": { "TorchPPOOptimizer.update": { "total": 118.34496836999301, "count": 4587, "is_parallel": true, "self": 118.34496836999301 } } } } } } } } }, "TrainerController._save_models": { "total": 0.132949397999937, "count": 1, "self": 0.0008655389999603358, "children": { "RLTrainer._checkpoint": { "total": 0.13208385899997666, "count": 1, "self": 0.13208385899997666 } } } } } } }