{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8161167502403259, "min": 0.8161167502403259, "max": 2.8585546016693115, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7756.37353515625, "min": 7756.37353515625, "max": 29180.125, "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": 13.098285675048828, "min": 0.3298819363117218, "max": 13.098285675048828, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2554.165771484375, "min": 63.997093200683594, "max": 2633.009765625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.061522224684035884, "min": 0.061522224684035884, "max": 0.07457766139911351, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24608889873614354, "min": 0.24608889873614354, "max": 0.365939632058001, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21251005547888138, "min": 0.1277740083123539, "max": 0.2776420445418825, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8500402219155255, "min": 0.5110960332494155, "max": 1.3882102227094126, "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": 25.931818181818183, "min": 3.590909090909091, "max": 26.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 158.0, "max": 1430.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 3.590909090909091, "max": 26.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 158.0, "max": 1430.0, "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": "1781879395", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781879841" }, "total": 445.3440240929999, "count": 1, "self": 0.484379276999789, "children": { "run_training.setup": { "total": 0.02761006500008989, "count": 1, "self": 0.02761006500008989 }, "TrainerController.start_learning": { "total": 444.83203475100004, "count": 1, "self": 0.3562927329815011, "children": { "TrainerController._reset_env": { "total": 2.873540289999937, "count": 1, "self": 2.873540289999937 }, "TrainerController.advance": { "total": 441.51634213901866, "count": 18192, "self": 0.3595363860160887, "children": { "env_step": { "total": 323.4505039380099, "count": 18192, "self": 252.92081392501427, "children": { "SubprocessEnvManager._take_step": { "total": 70.3215298089915, "count": 18192, "self": 1.2610685349898176, "children": { "TorchPolicy.evaluate": { "total": 69.06046127400168, "count": 18192, "self": 69.06046127400168 } } }, "workers": { "total": 0.20816020400411617, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 442.7762204439791, "count": 18192, "is_parallel": true, "self": 220.3359463689551, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005043532999934541, "count": 1, "is_parallel": true, "self": 0.0036264990001200204, "children": { "_process_rank_one_or_two_observation": { "total": 0.001417033999814521, "count": 10, "is_parallel": true, "self": 0.001417033999814521 } } }, "UnityEnvironment.step": { "total": 0.03669476499999291, "count": 1, "is_parallel": true, "self": 0.000576600000158578, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038717699999324395, "count": 1, "is_parallel": true, "self": 0.00038717699999324395 }, "communicator.exchange": { "total": 0.033806836999929146, "count": 1, "is_parallel": true, "self": 0.033806836999929146 }, "steps_from_proto": { "total": 0.0019241509999119444, "count": 1, "is_parallel": true, "self": 0.00038026200013518974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015438889997767546, "count": 10, "is_parallel": true, "self": 0.0015438889997767546 } } } } } } }, "UnityEnvironment.step": { "total": 222.44027407502404, "count": 18191, "is_parallel": true, "self": 10.228783218019316, "children": { "UnityEnvironment._generate_step_input": { "total": 5.519504707993065, "count": 18191, "is_parallel": true, "self": 5.519504707993065 }, "communicator.exchange": { "total": 169.95783962701717, "count": 18191, "is_parallel": true, "self": 169.95783962701717 }, "steps_from_proto": { "total": 36.73414652199449, "count": 18191, "is_parallel": true, "self": 6.601637779980138, "children": { "_process_rank_one_or_two_observation": { "total": 30.132508742014352, "count": 181910, "is_parallel": true, "self": 30.132508742014352 } } } } } } } } } } }, "trainer_advance": { "total": 117.70630181499268, "count": 18192, "self": 0.42301709899516027, "children": { "process_trajectory": { "total": 23.900873301997308, "count": 18192, "self": 23.473088096997344, "children": { "RLTrainer._checkpoint": { "total": 0.42778520499996375, "count": 4, "self": 0.42778520499996375 } } }, "_update_policy": { "total": 93.38241141400022, "count": 90, "self": 37.9081682289941, "children": { "TorchPPOOptimizer.update": { "total": 55.47424318500612, "count": 4587, "self": 55.47424318500612 } } } } } } }, "trainer_threads": { "total": 1.2569998943945393e-06, "count": 1, "self": 1.2569998943945393e-06 }, "TrainerController._save_models": { "total": 0.08585833200004345, "count": 1, "self": 0.000881941999978153, "children": { "RLTrainer._checkpoint": { "total": 0.0849763900000653, "count": 1, "self": 0.0849763900000653 } } } } } } }