{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5809351205825806, "min": 0.5809351205825806, "max": 1.4462707042694092, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17344.3984375, "min": 17344.3984375, "max": 43874.06640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29991.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29991.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4912666082382202, "min": -0.12400972843170166, "max": 0.49308890104293823, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.58958435058594, "min": -29.88634490966797, "max": 135.58958435058594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04117882251739502, "min": -0.04117882251739502, "max": 0.32481133937835693, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.365354537963867, "min": -11.365354537963867, "max": 77.30509948730469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0677176673530734, "min": 0.06554015136412893, "max": 0.07301532093777764, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9480473429430276, "min": 0.4780482198854362, "max": 1.0580298129729377, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016326276119105473, "min": 0.00014472625689507525, "max": 0.016326276119105473, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22856786566747664, "min": 0.0018814413396359782, "max": 0.22856786566747664, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.572461761592858e-06, "min": 7.572461761592858e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010601446466230002, "min": 0.00010601446466230002, "max": 0.0035070941309687, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252412142857144, "min": 0.10252412142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353377, "min": 1.3886848, "max": 2.5690313000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002621597307142858, "min": 0.0002621597307142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003670236230000001, "min": 0.003670236230000001, "max": 0.11692622687000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012825727462768555, "min": 0.012825727462768555, "max": 0.4065520465373993, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17956018447875977, "min": 0.17956018447875977, "max": 2.8458642959594727, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 369.3255813953488, "min": 369.3255813953488, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31762.0, "min": 16790.0, "max": 33327.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5187815882522484, "min": -0.9998125517740846, "max": 1.5999653130769729, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.1339981779456, "min": -31.994001656770706, "max": 132.1339981779456, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5187815882522484, "min": -0.9998125517740846, "max": 1.5999653130769729, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.1339981779456, "min": -31.994001656770706, "max": 132.1339981779456, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04811250005300751, "min": 0.04811250005300751, "max": 7.843354196232908, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.185787504611653, "min": 3.9950330543215387, "max": 133.33702133595943, "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": "1729018971", "python_version": "3.10.12 (main, Oct 15 2024, 18:54:33) [GCC 13.2.0]", "command_line_arguments": "/home/floflo/Documents/projects/rl_lesson/rl-venv3.10.12/bin/mlagents-learn ./ml-agents/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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729020255" }, "total": 1284.3942436789985, "count": 1, "self": 0.2721919949981384, "children": { "run_training.setup": { "total": 0.017630377999012126, "count": 1, "self": 0.017630377999012126 }, "TrainerController.start_learning": { "total": 1284.1044213060013, "count": 1, "self": 1.4537575926224235, "children": { "TrainerController._reset_env": { "total": 1.3305720169992128, "count": 1, "self": 1.3305720169992128 }, "TrainerController.advance": { "total": 1281.2508628493815, "count": 63550, "self": 1.516188487476029, "children": { "env_step": { "total": 782.025352162982, "count": 63550, "self": 652.4317618878376, "children": { "SubprocessEnvManager._take_step": { "total": 128.6693573256889, "count": 63550, "self": 3.8632526326509833, "children": { "TorchPolicy.evaluate": { "total": 124.80610469303792, "count": 62554, "self": 124.80610469303792 } } }, "workers": { "total": 0.9242329494554724, "count": 63550, "self": 0.0, "children": { "worker_root": { "total": 1282.1158684362636, "count": 63550, "is_parallel": true, "self": 721.173446109824, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013749369973083958, "count": 1, "is_parallel": true, "self": 0.00034774300002027303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010271939972881228, "count": 8, "is_parallel": true, "self": 0.0010271939972881228 } } }, "UnityEnvironment.step": { "total": 0.02707975000157603, "count": 1, "is_parallel": true, "self": 0.00046023599861655384, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021328100046957843, "count": 1, "is_parallel": true, "self": 0.00021328100046957843 }, "communicator.exchange": { "total": 0.02533980600128416, "count": 1, "is_parallel": true, "self": 0.02533980600128416 }, "steps_from_proto": { "total": 0.0010664270012057386, "count": 1, "is_parallel": true, "self": 0.00022875099966768175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008376760015380569, "count": 8, "is_parallel": true, "self": 0.0008376760015380569 } } } } } } }, "UnityEnvironment.step": { "total": 560.9424223264396, "count": 63549, "is_parallel": true, "self": 17.480993769553606, "children": { "UnityEnvironment._generate_step_input": { "total": 16.02624172081778, "count": 63549, "is_parallel": true, "self": 16.02624172081778 }, "communicator.exchange": { "total": 475.5890782370989, "count": 63549, "is_parallel": true, "self": 475.5890782370989 }, "steps_from_proto": { "total": 51.846108598969295, "count": 63549, "is_parallel": true, "self": 11.880059176612122, "children": { "_process_rank_one_or_two_observation": { "total": 39.96604942235717, "count": 508392, "is_parallel": true, "self": 39.96604942235717 } } } } } } } } } } }, "trainer_advance": { "total": 497.7093221989235, "count": 63550, "self": 2.872890159356757, "children": { "process_trajectory": { "total": 94.62628681554634, "count": 63550, "self": 94.44925857154522, "children": { "RLTrainer._checkpoint": { "total": 0.1770282440011215, "count": 2, "self": 0.1770282440011215 } } }, "_update_policy": { "total": 400.2101452240204, "count": 448, "self": 229.2705417259458, "children": { "TorchPPOOptimizer.update": { "total": 170.93960349807458, "count": 22797, "self": 170.93960349807458 } } } } } } }, "trainer_threads": { "total": 7.019989425316453e-07, "count": 1, "self": 7.019989425316453e-07 }, "TrainerController._save_models": { "total": 0.06922814499921515, "count": 1, "self": 0.001165250996564282, "children": { "RLTrainer._checkpoint": { "total": 0.06806289400265086, "count": 1, "self": 0.06806289400265086 } } } } } } }