{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3324096202850342, "min": 0.3324096202850342, "max": 1.3773709535598755, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9977.607421875, "min": 9977.607421875, "max": 41783.92578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989966.0, "min": 29952.0, "max": 989966.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989966.0, "min": 29952.0, "max": 989966.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6785151362419128, "min": -0.10306501388549805, "max": 0.6785151362419128, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 196.09088134765625, "min": -24.838668823242188, "max": 196.09088134765625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.032506633549928665, "min": -0.032506633549928665, "max": 0.42344930768013, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.394416809082031, "min": -9.394416809082031, "max": 100.35748291015625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06950141442732206, "min": 0.06565326363011655, "max": 0.07543496782924738, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9730198019825089, "min": 0.49066300896844744, "max": 1.0751715362729397, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015589613147874383, "min": 0.00027823362999343764, "max": 0.015589613147874383, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21825458407024137, "min": 0.0033388035599212517, "max": 0.22541765672697991, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.527054633871425e-06, "min": 7.527054633871425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010537876487419995, "min": 0.00010537876487419995, "max": 0.0033828182723940003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250898571428571, "min": 0.10250898571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351258, "min": 1.3691136000000002, "max": 2.5276060000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002606476728571428, "min": 0.0002606476728571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003649067419999999, "min": 0.003649067419999999, "max": 0.1127878394, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016330702230334282, "min": 0.016330702230334282, "max": 0.5242859721183777, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22862982749938965, "min": 0.22862982749938965, "max": 3.670001983642578, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 269.0093457943925, "min": 269.0093457943925, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28784.0, "min": 15984.0, "max": 31968.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7132703541881509, "min": -1.0000000521540642, "max": 1.7132703541881509, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.0331982523203, "min": -32.000001668930054, "max": 185.0331982523203, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7132703541881509, "min": -1.0000000521540642, "max": 1.7132703541881509, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.0331982523203, "min": -32.000001668930054, "max": 185.0331982523203, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04521450751161427, "min": 0.04521450751161427, "max": 10.2207016851753, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.883166811254341, "min": 4.883166811254341, "max": 163.5312269628048, "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": "1752030534", "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=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752032857" }, "total": 2323.268537903, "count": 1, "self": 0.7319118929999604, "children": { "run_training.setup": { "total": 0.019756632000053287, "count": 1, "self": 0.019756632000053287 }, "TrainerController.start_learning": { "total": 2322.516869378, "count": 1, "self": 1.3272841248995064, "children": { "TrainerController._reset_env": { "total": 2.1195560619999014, "count": 1, "self": 2.1195560619999014 }, "TrainerController.advance": { "total": 2318.9390377751006, "count": 64013, "self": 1.4261051260782551, "children": { "env_step": { "total": 1647.3051999099216, "count": 64013, "self": 1493.9641580559958, "children": { "SubprocessEnvManager._take_step": { "total": 152.52593543200828, "count": 64013, "self": 4.632435542934445, "children": { "TorchPolicy.evaluate": { "total": 147.89349988907384, "count": 62562, "self": 147.89349988907384 } } }, "workers": { "total": 0.8151064219175623, "count": 64013, "self": 0.0, "children": { "worker_root": { "total": 2317.0221504949554, "count": 64013, "is_parallel": true, "self": 938.8044215899886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017504460001873667, "count": 1, "is_parallel": true, "self": 0.0005557680003676069, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011946779998197599, "count": 8, "is_parallel": true, "self": 0.0011946779998197599 } } }, "UnityEnvironment.step": { "total": 0.054098464000162494, "count": 1, "is_parallel": true, "self": 0.0005369260002225928, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005270599999676051, "count": 1, "is_parallel": true, "self": 0.0005270599999676051 }, "communicator.exchange": { "total": 0.05151604699995005, "count": 1, "is_parallel": true, "self": 0.05151604699995005 }, "steps_from_proto": { "total": 0.0015184310000222467, "count": 1, "is_parallel": true, "self": 0.0003280480002558761, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011903829997663706, "count": 8, "is_parallel": true, "self": 0.0011903829997663706 } } } } } } }, "UnityEnvironment.step": { "total": 1378.2177289049669, "count": 64012, "is_parallel": true, "self": 32.417264447978596, "children": { "UnityEnvironment._generate_step_input": { "total": 23.785805463995985, "count": 64012, "is_parallel": true, "self": 23.785805463995985 }, "communicator.exchange": { "total": 1223.4500049539856, "count": 64012, "is_parallel": true, "self": 1223.4500049539856 }, "steps_from_proto": { "total": 98.56465403900665, "count": 64012, "is_parallel": true, "self": 19.74411246511704, "children": { "_process_rank_one_or_two_observation": { "total": 78.82054157388961, "count": 512096, "is_parallel": true, "self": 78.82054157388961 } } } } } } } } } } }, "trainer_advance": { "total": 670.2077327391007, "count": 64013, "self": 2.5984472541399555, "children": { "process_trajectory": { "total": 128.9299567909609, "count": 64013, "self": 128.68785319096128, "children": { "RLTrainer._checkpoint": { "total": 0.2421035999996093, "count": 2, "self": 0.2421035999996093 } } }, "_update_policy": { "total": 538.6793286939999, "count": 448, "self": 300.47410415498416, "children": { "TorchPPOOptimizer.update": { "total": 238.20522453901572, "count": 22857, "self": 238.20522453901572 } } } } } } }, "trainer_threads": { "total": 1.4650004231953062e-06, "count": 1, "self": 1.4650004231953062e-06 }, "TrainerController._save_models": { "total": 0.13098995099971944, "count": 1, "self": 0.001949931999661203, "children": { "RLTrainer._checkpoint": { "total": 0.12904001900005824, "count": 1, "self": 0.12904001900005824 } } } } } } }