{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1432248204946518, "min": 0.1379471868276596, "max": 1.3595614433288574, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4260.0791015625, "min": 4131.7939453125, "max": 41243.65625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999912.0, "min": 29952.0, "max": 2999912.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999912.0, "min": 29952.0, "max": 2999912.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 1.100515604019165, "min": -0.16910748183727264, "max": 1.2134467363357544, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 325.75262451171875, "min": -40.92401123046875, "max": 375.9116516113281, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016255339607596397, "min": 0.002779280534014106, "max": 0.8193689584732056, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.811580657958984, "min": 0.8115499019622803, "max": 198.28729248046875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06756768655773782, "min": 0.0648639870655415, "max": 0.07387066885366082, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9459476118083294, "min": 0.4998324553523381, "max": 1.0797932935529388, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00987718583779874, "min": 0.0006425859543907642, "max": 0.01247285795557027, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13828060172918236, "min": 0.00771103145268917, "max": 0.1834638506475398, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5289709189476186e-06, "min": 1.5289709189476186e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.140559286526666e-05, "min": 2.140559286526666e-05, "max": 0.004052995049001666, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050962380952384, "min": 0.10050962380952384, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071347333333337, "min": 1.3962282666666668, "max": 2.812516933333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.091141857142856e-05, "min": 6.091141857142856e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008527598599999998, "min": 0.0008527598599999998, "max": 0.1351047335, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01093019638210535, "min": 0.010167845524847507, "max": 0.629494845867157, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15302275121212006, "min": 0.14234983921051025, "max": 4.406464099884033, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 225.14285714285714, "min": 203.2972972972973, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29944.0, "min": 15984.0, "max": 33041.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7447729180181832, "min": -1.0000000521540642, "max": 1.7967026900198009, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 232.05479809641838, "min": -28.441401720046997, "max": 265.9119981229305, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7447729180181832, "min": -1.0000000521540642, "max": 1.7967026900198009, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 232.05479809641838, "min": -28.441401720046997, "max": 265.9119981229305, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025980279368656527, "min": 0.024202686452441287, "max": 13.515965981408954, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 3.455377156031318, "min": 3.0913007008784916, "max": 216.25545570254326, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717150142", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717157859" }, "total": 7717.838735091, "count": 1, "self": 0.8874487940001927, "children": { "run_training.setup": { "total": 0.053547968999964723, "count": 1, "self": 0.053547968999964723 }, "TrainerController.start_learning": { "total": 7716.897738328, "count": 1, "self": 4.532014189103393, "children": { "TrainerController._reset_env": { "total": 2.3423919560000286, "count": 1, "self": 2.3423919560000286 }, "TrainerController.advance": { "total": 7709.827052239894, "count": 195558, "self": 4.536218049057425, "children": { "env_step": { "total": 5706.810530603821, "count": 195558, "self": 5292.372043393619, "children": { "SubprocessEnvManager._take_step": { "total": 411.67344595391137, "count": 195558, "self": 14.33178331199747, "children": { "TorchPolicy.evaluate": { "total": 397.3416626419139, "count": 187554, "self": 397.3416626419139 } } }, "workers": { "total": 2.76504125629026, "count": 195558, "self": 0.0, "children": { "worker_root": { "total": 7699.594466225703, "count": 195558, "is_parallel": true, "self": 2793.9669094147866, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002089996999984578, "count": 1, "is_parallel": true, "self": 0.0006504669997866586, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014395300001979194, "count": 8, "is_parallel": true, "self": 0.0014395300001979194 } } }, "UnityEnvironment.step": { "total": 0.047976537000067765, "count": 1, "is_parallel": true, "self": 0.0006176310000682861, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046911999993426434, "count": 1, "is_parallel": true, "self": 0.00046911999993426434 }, "communicator.exchange": { "total": 0.045195610000064335, "count": 1, "is_parallel": true, "self": 0.045195610000064335 }, "steps_from_proto": { "total": 0.0016941760000008799, "count": 1, "is_parallel": true, "self": 0.00041533700004947605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012788389999514038, "count": 8, "is_parallel": true, "self": 0.0012788389999514038 } } } } } } }, "UnityEnvironment.step": { "total": 4905.627556810917, "count": 195557, "is_parallel": true, "self": 104.83164177845447, "children": { "UnityEnvironment._generate_step_input": { "total": 70.31450678442434, "count": 195557, "is_parallel": true, "self": 70.31450678442434 }, "communicator.exchange": { "total": 4430.451494534862, "count": 195557, "is_parallel": true, "self": 4430.451494534862 }, "steps_from_proto": { "total": 300.02991371317603, "count": 195557, "is_parallel": true, "self": 62.20493161995046, "children": { "_process_rank_one_or_two_observation": { "total": 237.82498209322557, "count": 1564456, "is_parallel": true, "self": 237.82498209322557 } } } } } } } } } } }, "trainer_advance": { "total": 1998.480303587016, "count": 195558, "self": 8.877730591067575, "children": { "process_trajectory": { "total": 407.32850063992396, "count": 195558, "self": 406.5421406149237, "children": { "RLTrainer._checkpoint": { "total": 0.7863600250002492, "count": 6, "self": 0.7863600250002492 } } }, "_update_policy": { "total": 1582.2740723560244, "count": 1403, "self": 908.8721937990156, "children": { "TorchPPOOptimizer.update": { "total": 673.4018785570088, "count": 68301, "self": 673.4018785570088 } } } } } } }, "trainer_threads": { "total": 1.3490007404470816e-06, "count": 1, "self": 1.3490007404470816e-06 }, "TrainerController._save_models": { "total": 0.19627859400134184, "count": 1, "self": 0.0035659960012708325, "children": { "RLTrainer._checkpoint": { "total": 0.192712598000071, "count": 1, "self": 0.192712598000071 } } } } } } }