{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5976666212081909, "min": 0.5976666212081909, "max": 1.4161652326583862, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17776.99609375, "min": 17776.99609375, "max": 42960.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36670488119125366, "min": -0.25694480538368225, "max": 0.4105684757232666, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 96.4433822631836, "min": -60.89591979980469, "max": 109.95828247070312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.2651892304420471, "min": -0.2651892304420471, "max": 0.4213647246360779, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -69.74476623535156, "min": -69.74476623535156, "max": 99.86344146728516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07070354652458656, "min": 0.06497799776244553, "max": 0.07368903074764122, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9898496513442118, "min": 0.4733976077625592, "max": 1.070244202176885, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.07504475636363549, "min": 0.00021381127692296324, "max": 0.07504475636363549, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.0506265890908968, "min": 0.0023519240461525957, "max": 1.0506265890908968, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.457797514099996e-06, "min": 7.457797514099996e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010440916519739994, "min": 0.00010440916519739994, "max": 0.0033817625727458993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024859, "min": 0.1024859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348026, "min": 1.3691136000000002, "max": 2.5272541000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025834140999999986, "min": 0.00025834140999999986, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036167797399999984, "min": 0.0036167797399999984, "max": 0.11275268459000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011050209403038025, "min": 0.010974555276334286, "max": 0.5298849940299988, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15470293164253235, "min": 0.15364377200603485, "max": 3.709195137023926, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 461.5967741935484, "min": 411.71014492753625, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28619.0, "min": 15984.0, "max": 32176.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.409332235734309, "min": -1.0000000521540642, "max": 1.4475128796071774, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.37859861552715, "min": -32.000001668930054, "max": 97.38299848884344, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.409332235734309, "min": -1.0000000521540642, "max": 1.4475128796071774, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.37859861552715, "min": -32.000001668930054, "max": 97.38299848884344, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05262449718335824, "min": 0.0493061040765107, "max": 10.478672744706273, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2627188253682107, "min": 3.2627188253682107, "max": 167.65876391530037, "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": "1776891307", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/home/hamzachera/repos/deep-rl/.venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1776893487" }, "total": 2179.843266985001, "count": 1, "self": 5.287105398994754, "children": { "run_training.setup": { "total": 0.028407500001776498, "count": 1, "self": 0.028407500001776498 }, "TrainerController.start_learning": { "total": 2174.5277540860043, "count": 1, "self": 1.3379652063231333, "children": { "TrainerController._reset_env": { "total": 3.101773079004488, "count": 1, "self": 3.101773079004488 }, "TrainerController.advance": { "total": 2169.912901101685, "count": 63515, "self": 1.3016575017827563, "children": { "env_step": { "total": 1147.2413746621314, "count": 63515, "self": 838.7020583442645, "children": { "SubprocessEnvManager._take_step": { "total": 307.66693021857645, "count": 63515, "self": 4.961511002933548, "children": { "TorchPolicy.evaluate": { "total": 302.7054192156429, "count": 62552, "self": 302.7054192156429 } } }, "workers": { "total": 0.872386099290452, "count": 63515, "self": 0.0, "children": { "worker_root": { "total": 2171.070192884981, "count": 63515, "is_parallel": true, "self": 1424.3838945085736, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002793699997710064, "count": 1, "is_parallel": true, "self": 0.0010844999997061677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017091999980038963, "count": 8, "is_parallel": true, "self": 0.0017091999980038963 } } }, "UnityEnvironment.step": { "total": 0.04521950000344077, "count": 1, "is_parallel": true, "self": 0.00032079999800771475, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002604000037536025, "count": 1, "is_parallel": true, "self": 0.0002604000037536025 }, "communicator.exchange": { "total": 0.0434462999983225, "count": 1, "is_parallel": true, "self": 0.0434462999983225 }, "steps_from_proto": { "total": 0.0011920000033569522, "count": 1, "is_parallel": true, "self": 0.0003201000072294846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008718999961274676, "count": 8, "is_parallel": true, "self": 0.0008718999961274676 } } } } } } }, "UnityEnvironment.step": { "total": 746.6862983764076, "count": 63514, "is_parallel": true, "self": 16.59875050491246, "children": { "UnityEnvironment._generate_step_input": { "total": 12.790945012027805, "count": 63514, "is_parallel": true, "self": 12.790945012027805 }, "communicator.exchange": { "total": 668.5565074122205, "count": 63514, "is_parallel": true, "self": 668.5565074122205 }, "steps_from_proto": { "total": 48.74009544724686, "count": 63514, "is_parallel": true, "self": 11.422874814052193, "children": { "_process_rank_one_or_two_observation": { "total": 37.317220633194665, "count": 508112, "is_parallel": true, "self": 37.317220633194665 } } } } } } } } } } }, "trainer_advance": { "total": 1021.3698689377707, "count": 63515, "self": 2.307490106431942, "children": { "process_trajectory": { "total": 153.06207460445876, "count": 63515, "self": 152.71894820345915, "children": { "RLTrainer._checkpoint": { "total": 0.34312640099960845, "count": 2, "self": 0.34312640099960845 } } }, "_update_policy": { "total": 866.00030422688, "count": 446, "self": 329.1337724230689, "children": { "TorchPPOOptimizer.update": { "total": 536.8665318038111, "count": 22863, "self": 536.8665318038111 } } } } } } }, "trainer_threads": { "total": 6.999980541877449e-07, "count": 1, "self": 6.999980541877449e-07 }, "TrainerController._save_models": { "total": 0.17511399899376556, "count": 1, "self": 0.001749099996231962, "children": { "RLTrainer._checkpoint": { "total": 0.1733648989975336, "count": 1, "self": 0.1733648989975336 } } } } } } }