{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4998490810394287, "min": 0.4728173017501831, "max": 1.4580899477005005, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15043.4580078125, "min": 14237.474609375, "max": 44232.6171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29983.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29983.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2735965847969055, "min": -0.1106395274400711, "max": 0.29286447167396545, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.1351089477539, "min": -26.664125442504883, "max": 74.3875732421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.034446023404598236, "min": 0.011637752875685692, "max": 0.33293867111206055, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.955965995788574, "min": 2.955989122390747, "max": 79.2394027709961, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06774516822028374, "min": 0.06390888027395827, "max": 0.07277049920866974, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9484323550839725, "min": 0.48003731949299033, "max": 1.0595410776012988, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010847047726787658, "min": 0.00011240023208295882, "max": 0.010847047726787658, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15185866817502722, "min": 0.0015736032491614235, "max": 0.15185866817502722, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.560226051385713e-06, "min": 7.560226051385713e-06, "max": 0.0002952370730162143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010584316471939998, "min": 0.00010584316471939998, "max": 0.0033817742727419997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252004285714286, "min": 0.10252004285714286, "max": 0.19841235714285713, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352806, "min": 1.3888865, "max": 2.527258, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026175228142857144, "min": 0.00026175228142857144, "max": 0.009841394478571427, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00366453194, "min": 0.00366453194, "max": 0.1127530742, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016172276809811592, "min": 0.01579626277089119, "max": 0.42078861594200134, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2264118641614914, "min": 0.22114768624305725, "max": 2.9455204010009766, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 521.5833333333334, "min": 521.5833333333334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31295.0, "min": 16526.0, "max": 33195.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.011603310952584, "min": -0.9999500517733395, "max": 1.0499265009955483, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 60.69619865715504, "min": -31.998401656746864, "max": 60.69619865715504, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.011603310952584, "min": -0.9999500517733395, "max": 1.0499265009955483, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 60.69619865715504, "min": -31.998401656746864, "max": 60.69619865715504, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08584638049869682, "min": 0.08584638049869682, "max": 8.502948817523087, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.150782829921809, "min": 4.382882176010753, "max": 144.55012989789248, "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": "1775641717", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1775644175" }, "total": 2458.7961392909997, "count": 1, "self": 0.529840712999885, "children": { "run_training.setup": { "total": 0.024792724999997517, "count": 1, "self": 0.024792724999997517 }, "TrainerController.start_learning": { "total": 2458.2415058529996, "count": 1, "self": 1.620740601055786, "children": { "TrainerController._reset_env": { "total": 2.2551514990000214, "count": 1, "self": 2.2551514990000214 }, "TrainerController.advance": { "total": 2454.268330093944, "count": 63333, "self": 1.6589472269056387, "children": { "env_step": { "total": 1726.443126869043, "count": 63333, "self": 1550.6996559902168, "children": { "SubprocessEnvManager._take_step": { "total": 174.753622907901, "count": 63333, "self": 5.3960583648686224, "children": { "TorchPolicy.evaluate": { "total": 169.35756454303237, "count": 62554, "self": 169.35756454303237 } } }, "workers": { "total": 0.9898479709252115, "count": 63333, "self": 0.0, "children": { "worker_root": { "total": 2451.6542174919828, "count": 63333, "is_parallel": true, "self": 1036.9193373230612, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019013670000731508, "count": 1, "is_parallel": true, "self": 0.0005660070000885753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013353599999845756, "count": 8, "is_parallel": true, "self": 0.0013353599999845756 } } }, "UnityEnvironment.step": { "total": 0.05508255199993073, "count": 1, "is_parallel": true, "self": 0.0010825760000443552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000504071000023032, "count": 1, "is_parallel": true, "self": 0.000504071000023032 }, "communicator.exchange": { "total": 0.051618872999824816, "count": 1, "is_parallel": true, "self": 0.051618872999824816 }, "steps_from_proto": { "total": 0.0018770320000385254, "count": 1, "is_parallel": true, "self": 0.0004365929994492035, "children": { "_process_rank_one_or_two_observation": { "total": 0.001440439000589322, "count": 8, "is_parallel": true, "self": 0.001440439000589322 } } } } } } }, "UnityEnvironment.step": { "total": 1414.7348801689216, "count": 63332, "is_parallel": true, "self": 38.156549167969615, "children": { "UnityEnvironment._generate_step_input": { "total": 26.592376583997975, "count": 63332, "is_parallel": true, "self": 26.592376583997975 }, "communicator.exchange": { "total": 1223.4305275369707, "count": 63332, "is_parallel": true, "self": 1223.4305275369707 }, "steps_from_proto": { "total": 126.55542687998332, "count": 63332, "is_parallel": true, "self": 25.934962827198433, "children": { "_process_rank_one_or_two_observation": { "total": 100.62046405278488, "count": 506656, "is_parallel": true, "self": 100.62046405278488 } } } } } } } } } } }, "trainer_advance": { "total": 726.166255997995, "count": 63333, "self": 2.9151220540338727, "children": { "process_trajectory": { "total": 138.59598950496343, "count": 63333, "self": 138.39573979596275, "children": { "RLTrainer._checkpoint": { "total": 0.20024970900067274, "count": 2, "self": 0.20024970900067274 } } }, "_update_policy": { "total": 584.6551444389977, "count": 446, "self": 323.9309060180062, "children": { "TorchPPOOptimizer.update": { "total": 260.72423842099147, "count": 22821, "self": 260.72423842099147 } } } } } } }, "trainer_threads": { "total": 1.038999471347779e-06, "count": 1, "self": 1.038999471347779e-06 }, "TrainerController._save_models": { "total": 0.09728262000044197, "count": 1, "self": 0.0012766320005539455, "children": { "RLTrainer._checkpoint": { "total": 0.09600598799988802, "count": 1, "self": 0.09600598799988802 } } } } } } }