{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.24421432614326477, "min": 0.24421432614326477, "max": 1.8863502740859985, "count": 33 }, "PushBlock.Policy.Entropy.sum": { "value": 14652.859375, "min": 14652.859375, "max": 114448.640625, "count": 33 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 20.067553377668883, "min": 20.067553377668883, "max": 969.0, "count": 33 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 57333.0, "min": 31977.0, "max": 74698.0, "count": 33 }, "PushBlock.Step.mean": { "value": 1979988.0, "min": 59978.0, "max": 1979988.0, "count": 33 }, "PushBlock.Step.sum": { "value": 1979988.0, "min": 59978.0, "max": 1979988.0, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.mean": { "value": 4.43574857711792, "min": -0.08287250995635986, "max": 4.43574857711792, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.sum": { "value": 13045.537109375, "min": -78.7288818359375, "max": 13045.537109375, "count": 33 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.974078939050843, "min": -0.8184606399048459, "max": 4.974078939050843, "count": 33 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 14210.943528868258, "min": -27.009201116859913, "max": 14210.943528868258, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.974078939050843, "min": -0.8184606399048459, "max": 4.974078939050843, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 14210.943528868258, "min": -27.009201116859913, "max": 14210.943528868258, "count": 33 }, "PushBlock.Losses.PolicyLoss.mean": { "value": 0.06914282932538998, "min": 0.06581221147167399, "max": 0.0724467805867726, "count": 33 }, "PushBlock.Losses.PolicyLoss.sum": { "value": 2.0051420504363096, "min": 1.3764888311486796, "max": 2.062408553950566, "count": 33 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.08825529210306918, "min": 0.004315959238690934, "max": 0.34610461603317944, "count": 33 }, "PushBlock.Losses.ValueLoss.sum": { "value": 2.559403470989006, "min": 0.08200322553512773, "max": 9.765468163835797, "count": 33 }, "PushBlock.Policy.LearningRate.mean": { "value": 7.647381933663791e-06, "min": 7.647381933663791e-06, "max": 0.0002954501225692579, "count": 33 }, "PushBlock.Policy.LearningRate.sum": { "value": 0.00022177407607624995, "min": 0.00022177407607624995, "max": 0.0080454926181692, "count": 33 }, "PushBlock.Policy.Epsilon.mean": { "value": 0.10254909482758622, "min": 0.10254909482758622, "max": 0.19848337368421054, "count": 33 }, "PushBlock.Policy.Epsilon.sum": { "value": 2.9739237500000004, "min": 2.9739237500000004, "max": 5.5818308000000005, "count": 33 }, "PushBlock.Policy.Beta.mean": { "value": 0.0002646545732758621, "min": 0.0002646545732758621, "max": 0.009848489031052631, "count": 33 }, "PushBlock.Policy.Beta.sum": { "value": 0.007674982625000001, "min": 0.007674982625000001, "max": 0.26820489692000005, "count": 33 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1657522736", "python_version": "3.9.5 (default, Nov 23 2021, 15:27:38) \n[GCC 9.3.0]", "command_line_arguments": "/local_disk0/.ephemeral_nfs/envs/pythonEnv-ee56e90a-0315-4a40-b96e-22edf928bfe1/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock_Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.20.3", "end_time_seconds": "1657524340" }, "total": 1603.738202311, "count": 1, "self": 0.22505834000003233, "children": { "run_training.setup": { "total": 0.08131532400011565, "count": 1, "self": 0.08131532400011565 }, "TrainerController.start_learning": { "total": 1603.4318286469997, "count": 1, "self": 1.9964657010145856, "children": { "TrainerController._reset_env": { "total": 12.816405771000063, "count": 1, "self": 12.816405771000063 }, "TrainerController.advance": { "total": 1588.5727853319854, "count": 104777, "self": 1.8357637480544327, "children": { "env_step": { "total": 863.3501310339134, "count": 104777, "self": 767.3870687080384, "children": { "SubprocessEnvManager._take_step": { "total": 94.82335125994405, "count": 104777, "self": 3.8164133998823218, "children": { "TorchPolicy.evaluate": { "total": 91.00693786006173, "count": 62513, "self": 28.058251052059404, "children": { "TorchPolicy.sample_actions": { "total": 62.94868680800232, "count": 62513, "self": 62.94868680800232 } } } } }, "workers": { "total": 1.1397110659308964, "count": 104777, "self": 0.0, "children": { "worker_root": { "total": 1600.3352156909912, "count": 104777, "is_parallel": true, "self": 959.7376939719265, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022880589999658696, "count": 1, "is_parallel": true, "self": 0.0009811929999159474, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013068660000499221, "count": 4, "is_parallel": true, "self": 0.0013068660000499221 } } }, "UnityEnvironment.step": { "total": 0.021547336999901745, "count": 1, "is_parallel": true, "self": 0.0005465269998694566, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004563540001072397, "count": 1, "is_parallel": true, "self": 0.0004563540001072397 }, "communicator.exchange": { "total": 0.01921374099993045, "count": 1, "is_parallel": true, "self": 0.01921374099993045 }, "steps_from_proto": { "total": 0.0013307149999945977, "count": 1, "is_parallel": true, "self": 0.00023626999995940423, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010944450000351935, "count": 4, "is_parallel": true, "self": 0.0010944450000351935 } } } } } } }, "UnityEnvironment.step": { "total": 640.5975217190646, "count": 104776, "is_parallel": true, "self": 35.60832911709758, "children": { "UnityEnvironment._generate_step_input": { "total": 25.686976524978945, "count": 104776, "is_parallel": true, "self": 25.686976524978945 }, "communicator.exchange": { "total": 492.7609767309564, "count": 104776, "is_parallel": true, "self": 492.7609767309564 }, "steps_from_proto": { "total": 86.54123934603172, "count": 104776, "is_parallel": true, "self": 17.24731187121074, "children": { "_process_rank_one_or_two_observation": { "total": 69.29392747482098, "count": 419104, "is_parallel": true, "self": 69.29392747482098 } } } } } } } } } } }, "trainer_advance": { "total": 723.3868905500176, "count": 104777, "self": 2.906158070032234, "children": { "process_trajectory": { "total": 209.45736746998523, "count": 104777, "self": 209.25968244098408, "children": { "RLTrainer._checkpoint": { "total": 0.19768502900114981, "count": 4, "self": 0.19768502900114981 } } }, "_update_policy": { "total": 511.02336501000013, "count": 953, "self": 275.9814385969696, "children": { "TorchPPOOptimizer.update": { "total": 235.04192641303052, "count": 46284, "self": 235.04192641303052 } } } } } } }, "trainer_threads": { "total": 7.61999672249658e-07, "count": 1, "self": 7.61999672249658e-07 }, "TrainerController._save_models": { "total": 0.04617108100001133, "count": 1, "self": 0.0004729920001409482, "children": { "RLTrainer._checkpoint": { "total": 0.04569808899987038, "count": 1, "self": 0.04569808899987038 } } } } } } }