{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28574705123901367, "min": 0.28574705123901367, "max": 1.489496111869812, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8622.703125, "min": 8536.48046875, "max": 45185.35546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6825927495956421, "min": -0.2584071159362793, "max": 0.6825927495956421, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 199.31707763671875, "min": -61.24248504638672, "max": 199.31707763671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.07069949805736542, "min": -0.07069949805736542, "max": 0.2773478031158447, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -20.64425277709961, "min": -20.64425277709961, "max": 65.73143005371094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06393051159542697, "min": 0.06393051159542697, "max": 0.0726603557967135, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8950271623359775, "min": 0.46382972810985446, "max": 1.0781678717301513, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01791183072562474, "min": 0.0005323139824072157, "max": 0.01791183072562474, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25076563015874637, "min": 0.004258511859257725, "max": 0.25076563015874637, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.703476003635714e-06, "min": 7.703476003635714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010784866405089999, "min": 0.00010784866405089999, "max": 0.0035070014309995998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256779285714288, "min": 0.10256779285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359491000000002, "min": 1.3691136000000002, "max": 2.5690004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002665225064285715, "min": 0.0002665225064285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037313150900000007, "min": 0.0037313150900000007, "max": 0.11692313996000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011151714250445366, "min": 0.010731740854680538, "max": 0.3842255771160126, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15612399578094482, "min": 0.15024437010288239, "max": 2.6895790100097656, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 273.23148148148147, "min": 273.23148148148147, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29509.0, "min": 15984.0, "max": 32549.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7252803591088715, "min": -1.0000000521540642, "max": 1.7252803591088715, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 184.60499842464924, "min": -32.000001668930054, "max": 184.60499842464924, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7252803591088715, "min": -1.0000000521540642, "max": 1.7252803591088715, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 184.60499842464924, "min": -32.000001668930054, "max": 184.60499842464924, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03105816642903923, "min": 0.03105816642903923, "max": 8.055326864123344, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3232238079071976, "min": 3.2589325687731616, "max": 128.8852298259735, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679891353", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1679893546" }, "total": 2193.141807037, "count": 1, "self": 0.5483497120003449, "children": { "run_training.setup": { "total": 0.10962709399996129, "count": 1, "self": 0.10962709399996129 }, "TrainerController.start_learning": { "total": 2192.483830231, "count": 1, "self": 1.4019079920285549, "children": { "TrainerController._reset_env": { "total": 5.99916195600008, "count": 1, "self": 5.99916195600008 }, "TrainerController.advance": { "total": 2184.9920851009715, "count": 64174, "self": 1.4867077039939431, "children": { "env_step": { "total": 1551.6493607019602, "count": 64174, "self": 1441.8139035999907, "children": { "SubprocessEnvManager._take_step": { "total": 108.98667274196578, "count": 64174, "self": 4.615748994934393, "children": { "TorchPolicy.evaluate": { "total": 104.37092374703138, "count": 62545, "self": 104.37092374703138 } } }, "workers": { "total": 0.8487843600037195, "count": 64174, "self": 0.0, "children": { "worker_root": { "total": 2187.852335568959, "count": 64174, "is_parallel": true, "self": 859.6575801639915, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017933039998752065, "count": 1, "is_parallel": true, "self": 0.0005199849995278782, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012733190003473283, "count": 8, "is_parallel": true, "self": 0.0012733190003473283 } } }, "UnityEnvironment.step": { "total": 0.04605518400012443, "count": 1, "is_parallel": true, "self": 0.0005216920001203107, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004374860000098124, "count": 1, "is_parallel": true, "self": 0.0004374860000098124 }, "communicator.exchange": { "total": 0.04348350999998729, "count": 1, "is_parallel": true, "self": 0.04348350999998729 }, "steps_from_proto": { "total": 0.0016124960000070132, "count": 1, "is_parallel": true, "self": 0.0003603070001645392, "children": { "_process_rank_one_or_two_observation": { "total": 0.001252188999842474, "count": 8, "is_parallel": true, "self": 0.001252188999842474 } } } } } } }, "UnityEnvironment.step": { "total": 1328.1947554049675, "count": 64173, "is_parallel": true, "self": 31.07553783301364, "children": { "UnityEnvironment._generate_step_input": { "total": 22.55347486398591, "count": 64173, "is_parallel": true, "self": 22.55347486398591 }, "communicator.exchange": { "total": 1183.873539611996, "count": 64173, "is_parallel": true, "self": 1183.873539611996 }, "steps_from_proto": { "total": 90.69220309597199, "count": 64173, "is_parallel": true, "self": 19.279200201034655, "children": { "_process_rank_one_or_two_observation": { "total": 71.41300289493734, "count": 513384, "is_parallel": true, "self": 71.41300289493734 } } } } } } } } } } }, "trainer_advance": { "total": 631.8560166950172, "count": 64174, "self": 2.5287134220102416, "children": { "process_trajectory": { "total": 116.71242485200582, "count": 64174, "self": 116.50043679800592, "children": { "RLTrainer._checkpoint": { "total": 0.21198805399990306, "count": 2, "self": 0.21198805399990306 } } }, "_update_policy": { "total": 512.6148784210011, "count": 445, "self": 327.4807273070012, "children": { "TorchPPOOptimizer.update": { "total": 185.1341511139999, "count": 22806, "self": 185.1341511139999 } } } } } } }, "trainer_threads": { "total": 1.02400008472614e-06, "count": 1, "self": 1.02400008472614e-06 }, "TrainerController._save_models": { "total": 0.09067415799972878, "count": 1, "self": 0.0016524909997315262, "children": { "RLTrainer._checkpoint": { "total": 0.08902166699999725, "count": 1, "self": 0.08902166699999725 } } } } } } }