{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14624297618865967, "min": 0.14624297618865967, "max": 1.4647560119628906, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4429.4072265625, "min": 4429.4072265625, "max": 44434.83984375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999961.0, "min": 29952.0, "max": 2999961.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999961.0, "min": 29952.0, "max": 2999961.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8048204183578491, "min": -0.09897731989622116, "max": 0.8590055704116821, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 238.22683715820312, "min": -23.853534698486328, "max": 261.1376953125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003933842293918133, "min": -0.027270613238215446, "max": 0.41345709562301636, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.1644172668457031, "min": -8.099371910095215, "max": 97.98933410644531, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07051334704668816, "min": 0.06429423743355771, "max": 0.07545404697173377, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9871868586536342, "min": 0.48659723690472106, "max": 1.1318107045760066, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013090788689580569, "min": 0.00012420112438344576, "max": 0.01626293453672487, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18327104165412797, "min": 0.0013662123682179033, "max": 0.24394401805087304, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5376566303380957e-06, "min": 1.5376566303380957e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.152719282473334e-05, "min": 2.152719282473334e-05, "max": 0.0037177996607335, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051251904761904, "min": 0.10051251904761904, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071752666666666, "min": 1.3897045333333333, "max": 2.737489833333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.120065285714288e-05, "min": 6.120065285714288e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008568091400000004, "min": 0.0008568091400000004, "max": 0.12394272335000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004076735116541386, "min": 0.004063901957124472, "max": 0.3282770812511444, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05707429349422455, "min": 0.05689462646842003, "max": 2.2979395389556885, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 220.21875, "min": 217.84285714285716, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28188.0, "min": 15984.0, "max": 33669.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.779781237593852, "min": -1.0000000521540642, "max": 1.779781237593852, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 227.81199841201305, "min": -32.000001668930054, "max": 245.50119867920876, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.779781237593852, "min": -1.0000000521540642, "max": 1.779781237593852, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 227.81199841201305, "min": -32.000001668930054, "max": 245.50119867920876, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.00933070190561125, "min": 0.009300382798619467, "max": 6.441338911652565, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.19432984391824, "min": 1.19432984391824, "max": 103.06142258644104, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731688232", "python_version": "3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\songo\\Documents\\Python\\DeepRLCourse\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./build/UnityEnvironment --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1731692835" }, "total": 4603.306294100001, "count": 1, "self": 0.25035030000435654, "children": { "run_training.setup": { "total": 0.1570873999989999, "count": 1, "self": 0.1570873999989999 }, "TrainerController.start_learning": { "total": 4602.898856399997, "count": 1, "self": 3.2654007006676693, "children": { "TrainerController._reset_env": { "total": 4.993731700000353, "count": 1, "self": 4.993731700000353 }, "TrainerController.advance": { "total": 4594.527222799328, "count": 194290, "self": 2.8569732006544655, "children": { "env_step": { "total": 2418.813839399236, "count": 194290, "self": 1775.8495642986854, "children": { "SubprocessEnvManager._take_step": { "total": 640.8690928998167, "count": 194290, "self": 9.036510999510938, "children": { "TorchPolicy.evaluate": { "total": 631.8325819003057, "count": 187570, "self": 631.8325819003057 } } }, "workers": { "total": 2.0951822007336887, "count": 194290, "self": 0.0, "children": { "worker_root": { "total": 4595.95136709964, "count": 194290, "is_parallel": true, "self": 3041.8285563000045, "children": { "steps_from_proto": { "total": 0.0008488000003126217, "count": 1, "is_parallel": true, "self": 0.0001990000000660075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006498000002466142, "count": 8, "is_parallel": true, "self": 0.0006498000002466142 } } }, "UnityEnvironment.step": { "total": 1554.1219619996355, "count": 194290, "is_parallel": true, "self": 51.483499799524, "children": { "UnityEnvironment._generate_step_input": { "total": 34.75150880024921, "count": 194290, "is_parallel": true, "self": 34.75150880024921 }, "communicator.exchange": { "total": 1333.029609400386, "count": 194290, "is_parallel": true, "self": 1333.029609400386 }, "steps_from_proto": { "total": 134.85734399947614, "count": 194290, "is_parallel": true, "self": 26.87234490111223, "children": { "_process_rank_one_or_two_observation": { "total": 107.98499909836391, "count": 1554320, "is_parallel": true, "self": 107.98499909836391 } } } } } } } } } } }, "trainer_advance": { "total": 2172.856410199438, "count": 194290, "self": 6.307676598404214, "children": { "process_trajectory": { "total": 351.15190310101025, "count": 194290, "self": 350.5796433010091, "children": { "RLTrainer._checkpoint": { "total": 0.5722598000011203, "count": 6, "self": 0.5722598000011203 } } }, "_update_policy": { "total": 1815.3968305000235, "count": 1376, "self": 812.0426447996033, "children": { "TorchPPOOptimizer.update": { "total": 1003.3541857004202, "count": 68484, "self": 1003.3541857004202 } } } } } } }, "trainer_threads": { "total": 6.000009307172149e-07, "count": 1, "self": 6.000009307172149e-07 }, "TrainerController._save_models": { "total": 0.11250060000020312, "count": 1, "self": 0.03100059999997029, "children": { "RLTrainer._checkpoint": { "total": 0.08150000000023283, "count": 1, "self": 0.08150000000023283 } } } } } } }