{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.46375229954719543, "min": 0.45574644207954407, "max": 1.0814392566680908, "count": 180 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4769.6923828125, "min": 4401.59912109375, "max": 11063.123046875, "count": 180 }, "SnowballTarget.Step.mean": { "value": 1999968.0, "min": 209936.0, "max": 1999968.0, "count": 180 }, "SnowballTarget.Step.sum": { "value": 1999968.0, "min": 209936.0, "max": 1999968.0, "count": 180 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.209834098815918, "min": 12.157634735107422, "max": 14.46787166595459, "count": 180 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2898.80615234375, "min": 2334.265869140625, "max": 2951.44580078125, "count": 180 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 180 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 180 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06399754855808044, "min": 0.05901062570189299, "max": 0.07679679757611844, "count": 180 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3199877427904022, "min": 0.23604250280757197, "max": 0.3793868969021109, "count": 180 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14642081707715987, "min": 0.117783935813635, "max": 0.21434705712211627, "count": 180 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7321040853857994, "min": 0.47113574325454, "max": 1.009957022526685, "count": 180 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.16499761199997e-07, "min": 7.16499761199997e-07, "max": 0.00026917141027619996, "count": 180 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.582498805999985e-06, "min": 3.582498805999985e-06, "max": 0.0013384320538559998, "count": 180 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1002388, "min": 0.1002388, "max": 0.1897238, "count": 180 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.501194, "min": 0.40293520000000005, "max": 0.9461439999999999, "count": 180 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1916119999999956e-05, "min": 2.1916119999999956e-05, "max": 0.00448721762, "count": 180 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010958059999999978, "min": 0.00010958059999999978, "max": 0.022312585599999997, "count": 180 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.472727272727273, "min": 24.636363636363637, "max": 28.490909090909092, "count": 180 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1566.0, "min": 1084.0, "max": 1567.0, "count": 180 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.472727272727273, "min": 24.636363636363637, "max": 28.490909090909092, "count": 180 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1566.0, "min": 1084.0, "max": 1567.0, "count": 180 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 180 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 180 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688432872", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "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": "1688436879" }, "total": 4007.6694433659995, "count": 1, "self": 0.4354427950001991, "children": { "run_training.setup": { "total": 0.03948715199999242, "count": 1, "self": 0.03948715199999242 }, "TrainerController.start_learning": { "total": 4007.1945134189996, "count": 1, "self": 4.813716734885475, "children": { "TrainerController._reset_env": { "total": 5.126784344000043, "count": 1, "self": 5.126784344000043 }, "TrainerController.advance": { "total": 3997.121896267113, "count": 163675, "self": 2.3122272430787234, "children": { "env_step": { "total": 3994.809669024034, "count": 163675, "self": 2901.543199972999, "children": { "SubprocessEnvManager._take_step": { "total": 1090.9602893359938, "count": 163675, "self": 15.401948041756668, "children": { "TorchPolicy.evaluate": { "total": 1075.5583412942372, "count": 163675, "self": 1075.5583412942372 } } }, "workers": { "total": 2.306179715041253, "count": 163675, "self": 0.0, "children": { "worker_root": { "total": 3995.0013063790384, "count": 163675, "is_parallel": true, "self": 1840.0155372449708, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030741819998638675, "count": 1, "is_parallel": true, "self": 0.0008424229997672228, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022317590000966447, "count": 10, "is_parallel": true, "self": 0.0022317590000966447 } } }, "UnityEnvironment.step": { "total": 0.088115180999921, "count": 1, "is_parallel": true, "self": 0.0006227889998626779, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047591199995622446, "count": 1, "is_parallel": true, "self": 0.00047591199995622446 }, "communicator.exchange": { "total": 0.08491159200002585, "count": 1, "is_parallel": true, "self": 0.08491159200002585 }, "steps_from_proto": { "total": 0.0021048880000762438, "count": 1, "is_parallel": true, "self": 0.0003696969997690758, "children": { "_process_rank_one_or_two_observation": { "total": 0.001735191000307168, "count": 10, "is_parallel": true, "self": 0.001735191000307168 } } } } } } }, "UnityEnvironment.step": { "total": 2154.9857691340676, "count": 163674, "is_parallel": true, "self": 88.49871801279005, "children": { "UnityEnvironment._generate_step_input": { "total": 45.35234410201474, "count": 163674, "is_parallel": true, "self": 45.35234410201474 }, "communicator.exchange": { "total": 1721.5845219941732, "count": 163674, "is_parallel": true, "self": 1721.5845219941732 }, "steps_from_proto": { "total": 299.5501850250896, "count": 163674, "is_parallel": true, "self": 53.8238223676135, "children": { "_process_rank_one_or_two_observation": { "total": 245.7263626574761, "count": 1636740, "is_parallel": true, "self": 245.7263626574761 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003110820007350412, "count": 1, "self": 0.0003110820007350412, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3967.208904714513, "count": 3778109, "is_parallel": true, "self": 83.18554804265796, "children": { "process_trajectory": { "total": 2177.3550886028543, "count": 3778109, "is_parallel": true, "self": 2167.0833852678543, "children": { "RLTrainer._checkpoint": { "total": 10.271703334999756, "count": 36, "is_parallel": true, "self": 10.271703334999756 } } }, "_update_policy": { "total": 1706.6682680690008, "count": 818, "is_parallel": true, "self": 623.4261155330423, "children": { "TorchPPOOptimizer.update": { "total": 1083.2421525359584, "count": 41709, "is_parallel": true, "self": 1083.2421525359584 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13180499100053567, "count": 1, "self": 0.001060339001014654, "children": { "RLTrainer._checkpoint": { "total": 0.130744651999521, "count": 1, "self": 0.130744651999521 } } } } } } }