{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4861375391483307, "min": 0.3695864975452423, "max": 0.4861375391483307, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 14506.34375, "min": 4839.00341796875, "max": 14506.34375, "count": 17 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 509972.0, "max": 989980.0, "count": 17 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 509972.0, "max": 989980.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03695984184741974, "min": -0.08555169403553009, "max": -0.006013940088450909, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -8.981241226196289, "min": -20.617958068847656, "max": -1.4613873958587646, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018821213394403458, "min": 0.006880927365273237, "max": 0.03625857084989548, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.573554992675781, "min": 1.6720653772354126, "max": 8.555917739868164, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04372363503734094, "min": 0.04350741712528, "max": 0.05727682797199425, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6121308905227731, "min": 0.1145536559439885, "max": 0.7122163788687128, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0033891489216503466, "min": 0.00012275117004329722, "max": 0.004827932314606001, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04744808490310485, "min": 0.0017185163806061612, "max": 0.06742017269546825, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.593397468899999e-06, "min": 7.593397468899999e-06, "max": 0.0001484448505184, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001063075645646, "min": 0.0001063075645646, "max": 0.0017404487198507, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253109999999999, "min": 0.10253109999999999, "max": 0.1494816, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354353999999998, "min": 0.2989632, "max": 1.9801493000000003, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026285688999999997, "min": 0.00026285688999999997, "max": 0.004953211839999999, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.00367999646, "min": 0.00367999646, "max": 0.05809691506999999, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.018067551776766777, "min": 0.018067551776766777, "max": 0.03520922362804413, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2529457211494446, "min": 0.07041844725608826, "max": 0.41933268308639526, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 896.2058823529412, "min": 359.0, "max": 999.0, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30471.0, "min": 359.0, "max": 32531.0, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.4261647484758321, "min": -0.9996000509108266, "max": 1.6409999430179596, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -14.489601448178291, "min": -30.987601578235626, "max": 1.6409999430179596, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.4261647484758321, "min": -0.9996000509108266, "max": 1.6409999430179596, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -14.489601448178291, "min": -30.987601578235626, "max": 1.6409999430179596, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.16191048095660174, "min": 0.13955319300293922, "max": 0.32983473233659477, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 5.504956352524459, "min": 0.13955319300293922, "max": 11.214380899444222, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678960907", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/ckahmann/miniconda3/envs/reinforcementlearning/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678961710" }, "total": 802.8675551442429, "count": 1, "self": 0.270288179628551, "children": { "run_training.setup": { "total": 0.012378045357763767, "count": 1, "self": 0.012378045357763767 }, "TrainerController.start_learning": { "total": 802.5848889192566, "count": 1, "self": 0.6095943795517087, "children": { "TrainerController._reset_env": { "total": 2.4626196241006255, "count": 1, "self": 2.4626196241006255 }, "TrainerController.advance": { "total": 799.4504055865109, "count": 31649, "self": 0.5123024992644787, "children": { "env_step": { "total": 617.7830136399716, "count": 31649, "self": 579.4647767068818, "children": { "SubprocessEnvManager._take_step": { "total": 37.97459286544472, "count": 31649, "self": 1.784407407976687, "children": { "TorchPolicy.evaluate": { "total": 36.19018545746803, "count": 31315, "self": 36.19018545746803 } } }, "workers": { "total": 0.34364406764507294, "count": 31649, "self": 0.0, "children": { "worker_root": { "total": 801.0027983011678, "count": 31649, "is_parallel": true, "self": 266.9414753317833, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001230727881193161, "count": 1, "is_parallel": true, "self": 0.00037774816155433655, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008529797196388245, "count": 8, "is_parallel": true, "self": 0.0008529797196388245 } } }, "UnityEnvironment.step": { "total": 0.04297054000198841, "count": 1, "is_parallel": true, "self": 0.0002757050096988678, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005850065499544144, "count": 1, "is_parallel": true, "self": 0.0005850065499544144 }, "communicator.exchange": { "total": 0.0413089320063591, "count": 1, "is_parallel": true, "self": 0.0413089320063591 }, "steps_from_proto": { "total": 0.0008008964359760284, "count": 1, "is_parallel": true, "self": 0.00020205602049827576, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005988404154777527, "count": 8, "is_parallel": true, "self": 0.0005988404154777527 } } } } } } }, "UnityEnvironment.step": { "total": 534.0613229693845, "count": 31648, "is_parallel": true, "self": 18.290482008829713, "children": { "UnityEnvironment._generate_step_input": { "total": 12.550280952826142, "count": 31648, "is_parallel": true, "self": 12.550280952826142 }, "communicator.exchange": { "total": 450.5672222394496, "count": 31648, "is_parallel": true, "self": 450.5672222394496 }, "steps_from_proto": { "total": 52.653337768279016, "count": 31648, "is_parallel": true, "self": 11.565798714756966, "children": { "_process_rank_one_or_two_observation": { "total": 41.08753905352205, "count": 253184, "is_parallel": true, "self": 41.08753905352205 } } } } } } } } } } }, "trainer_advance": { "total": 181.1550894472748, "count": 31649, "self": 1.1183641459792852, "children": { "process_trajectory": { "total": 34.63052374869585, "count": 31649, "self": 34.557224965654314, "children": { "RLTrainer._checkpoint": { "total": 0.07329878304153681, "count": 1, "self": 0.07329878304153681 } } }, "_update_policy": { "total": 145.40620155259967, "count": 227, "self": 97.75593001674861, "children": { "TorchPPOOptimizer.update": { "total": 47.65027153585106, "count": 5634, "self": 47.65027153585106 } } } } } } }, "trainer_threads": { "total": 7.208436727523804e-07, "count": 1, "self": 7.208436727523804e-07 }, "TrainerController._save_models": { "total": 0.06226860824972391, "count": 1, "self": 0.0012328457087278366, "children": { "RLTrainer._checkpoint": { "total": 0.061035762540996075, "count": 1, "self": 0.061035762540996075 } } } } } } }