{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46896541118621826, "min": 0.4676147997379303, "max": 1.4508050680160522, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14219.03125, "min": 13961.107421875, "max": 44011.62109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29949.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29949.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48374414443969727, "min": -0.15709589421749115, "max": 0.560604989528656, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.09466552734375, "min": -37.231727600097656, "max": 155.8481903076172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02015371434390545, "min": -0.004914955236017704, "max": 0.5287313461303711, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.46165657043457, "min": -1.3073780536651611, "max": 125.309326171875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07152914199174291, "min": 0.06395299469177215, "max": 0.07269769949262637, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0014079878844009, "min": 0.4896441407949294, "max": 1.0633831686573103, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014273580249296392, "min": 0.001086788266647913, "max": 0.016471372862898057, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19983012349014947, "min": 0.014128247466422869, "max": 0.2305992200805728, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.468233224907146e-06, "min": 7.468233224907146e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010455526514870005, "min": 0.00010455526514870005, "max": 0.0036097179967606997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248937857142856, "min": 0.10248937857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348512999999998, "min": 1.3886848, "max": 2.5032392999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002586889192857145, "min": 0.0002586889192857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003621644870000003, "min": 0.003621644870000003, "max": 0.12033360607000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011106238700449467, "min": 0.011106238700449467, "max": 0.6694268584251404, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15548734366893768, "min": 0.15548734366893768, "max": 4.685987949371338, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 390.041095890411, "min": 360.6860465116279, "max": 992.7058823529412, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28473.0, "min": 16876.0, "max": 32671.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4455232676373768, "min": -0.9272061125798658, "max": 1.5912987488655397, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.52319853752851, "min": -30.597801715135574, "max": 128.8951986581087, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4455232676373768, "min": -0.9272061125798658, "max": 1.5912987488655397, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.52319853752851, "min": -30.597801715135574, "max": 128.8951986581087, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044702134693156266, "min": 0.044702134693156266, "max": 13.745698075960664, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2632558326004073, "min": 3.2632558326004073, "max": 233.6768672913313, "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": "1769894843", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1769896906" }, "total": 2063.656296211, "count": 1, "self": 0.4815245010004219, "children": { "run_training.setup": { "total": 0.022699046999832717, "count": 1, "self": 0.022699046999832717 }, "TrainerController.start_learning": { "total": 2063.152072663, "count": 1, "self": 1.2353335350417183, "children": { "TrainerController._reset_env": { "total": 2.0771235289998913, "count": 1, "self": 2.0771235289998913 }, "TrainerController.advance": { "total": 2059.7666574469586, "count": 63691, "self": 1.3272641409153039, "children": { "env_step": { "total": 1423.603041945006, "count": 63691, "self": 1287.215358927111, "children": { "SubprocessEnvManager._take_step": { "total": 135.65325966995874, "count": 63691, "self": 4.205614278946314, "children": { "TorchPolicy.evaluate": { "total": 131.44764539101243, "count": 62569, "self": 131.44764539101243 } } }, "workers": { "total": 0.7344233479361719, "count": 63691, "self": 0.0, "children": { "worker_root": { "total": 2056.698903306055, "count": 63691, "is_parallel": true, "self": 877.0607717521009, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017057510001450282, "count": 1, "is_parallel": true, "self": 0.0005499560002135695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011557949999314587, "count": 8, "is_parallel": true, "self": 0.0011557949999314587 } } }, "UnityEnvironment.step": { "total": 0.047022325999932946, "count": 1, "is_parallel": true, "self": 0.000526882000031037, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045650699985344545, "count": 1, "is_parallel": true, "self": 0.00045650699985344545 }, "communicator.exchange": { "total": 0.04447309400006816, "count": 1, "is_parallel": true, "self": 0.04447309400006816 }, "steps_from_proto": { "total": 0.0015658429999803047, "count": 1, "is_parallel": true, "self": 0.00035303500021655054, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012128079997637542, "count": 8, "is_parallel": true, "self": 0.0012128079997637542 } } } } } } }, "UnityEnvironment.step": { "total": 1179.638131553954, "count": 63690, "is_parallel": true, "self": 31.850512022943576, "children": { "UnityEnvironment._generate_step_input": { "total": 21.65617829803523, "count": 63690, "is_parallel": true, "self": 21.65617829803523 }, "communicator.exchange": { "total": 1028.0422416860015, "count": 63690, "is_parallel": true, "self": 1028.0422416860015 }, "steps_from_proto": { "total": 98.08919954697376, "count": 63690, "is_parallel": true, "self": 20.40977689089368, "children": { "_process_rank_one_or_two_observation": { "total": 77.67942265608008, "count": 509520, "is_parallel": true, "self": 77.67942265608008 } } } } } } } } } } }, "trainer_advance": { "total": 634.8363513610373, "count": 63691, "self": 2.353508391082869, "children": { "process_trajectory": { "total": 115.86544834995925, "count": 63691, "self": 115.67950298395886, "children": { "RLTrainer._checkpoint": { "total": 0.18594536600039646, "count": 2, "self": 0.18594536600039646 } } }, "_update_policy": { "total": 516.6173946199951, "count": 452, "self": 289.1633714440111, "children": { "TorchPPOOptimizer.update": { "total": 227.45402317598405, "count": 22782, "self": 227.45402317598405 } } } } } } }, "trainer_threads": { "total": 9.690002116258256e-07, "count": 1, "self": 9.690002116258256e-07 }, "TrainerController._save_models": { "total": 0.07295718299974396, "count": 1, "self": 0.0008974649999800022, "children": { "RLTrainer._checkpoint": { "total": 0.07205971799976396, "count": 1, "self": 0.07205971799976396 } } } } } } }