{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4578157365322113, "min": 0.45772504806518555, "max": 1.4397660493850708, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13705.171875, "min": 13705.171875, "max": 43676.7421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.475912868976593, "min": -0.10600502789020538, "max": 0.475912868976593, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.44830322265625, "min": -25.653217315673828, "max": 129.44830322265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07849494367837906, "min": -0.14818648993968964, "max": 0.4096418023109436, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.350624084472656, "min": -39.12123489379883, "max": 97.0851058959961, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07077368604086459, "min": 0.0649164928136, "max": 0.07344643555253887, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9908316045721043, "min": 0.5100925824673171, "max": 1.0497214667745591, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01639891611482278, "min": 0.0010251538157091055, "max": 0.01639891611482278, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2295848256075189, "min": 0.01332699960421837, "max": 0.2295848256075189, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.545397484899994e-06, "min": 7.545397484899994e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010563556478859992, "min": 0.00010563556478859992, "max": 0.0036322648892451004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251510000000001, "min": 0.10251510000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352114000000002, "min": 1.3886848, "max": 2.6107549000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002612584899999998, "min": 0.0002612584899999998, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003657618859999997, "min": 0.003657618859999997, "max": 0.12109441451000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00989049393683672, "min": 0.009860330261290073, "max": 0.39337998628616333, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13846690952777863, "min": 0.13804462552070618, "max": 2.753659963607788, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.0, "min": 382.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30942.0, "min": 15984.0, "max": 33529.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.543898745543427, "min": -1.0000000521540642, "max": 1.543898745543427, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.05579838901758, "min": -30.629601694643497, "max": 125.05579838901758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.543898745543427, "min": -1.0000000521540642, "max": 1.543898745543427, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.05579838901758, "min": -30.629601694643497, "max": 125.05579838901758, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039811436542493785, "min": 0.039811436542493785, "max": 7.635970950126648, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2247263599419966, "min": 2.978304910750012, "max": 122.17553520202637, "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": "1712194866", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712197007" }, "total": 2141.213752612, "count": 1, "self": 0.4771491100000276, "children": { "run_training.setup": { "total": 0.050523639999937586, "count": 1, "self": 0.050523639999937586 }, "TrainerController.start_learning": { "total": 2140.686079862, "count": 1, "self": 1.393840525037831, "children": { "TrainerController._reset_env": { "total": 2.2819836080000186, "count": 1, "self": 2.2819836080000186 }, "TrainerController.advance": { "total": 2136.9264527819623, "count": 63633, "self": 1.397954337905503, "children": { "env_step": { "total": 1517.4487644180474, "count": 63633, "self": 1382.5654206271145, "children": { "SubprocessEnvManager._take_step": { "total": 134.0332873100133, "count": 63633, "self": 4.798501269017834, "children": { "TorchPolicy.evaluate": { "total": 129.23478604099546, "count": 62563, "self": 129.23478604099546 } } }, "workers": { "total": 0.8500564809196476, "count": 63633, "self": 0.0, "children": { "worker_root": { "total": 2135.673101198907, "count": 63633, "is_parallel": true, "self": 876.0303160699059, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002226049000000785, "count": 1, "is_parallel": true, "self": 0.000667943000280502, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015581059997202829, "count": 8, "is_parallel": true, "self": 0.0015581059997202829 } } }, "UnityEnvironment.step": { "total": 0.07584219099999245, "count": 1, "is_parallel": true, "self": 0.0006719989999055542, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000493406000032337, "count": 1, "is_parallel": true, "self": 0.000493406000032337 }, "communicator.exchange": { "total": 0.07288076100007856, "count": 1, "is_parallel": true, "self": 0.07288076100007856 }, "steps_from_proto": { "total": 0.001796024999975998, "count": 1, "is_parallel": true, "self": 0.0003997339997567906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013962910002192075, "count": 8, "is_parallel": true, "self": 0.0013962910002192075 } } } } } } }, "UnityEnvironment.step": { "total": 1259.642785129001, "count": 63632, "is_parallel": true, "self": 34.64530551397797, "children": { "UnityEnvironment._generate_step_input": { "total": 25.06599376402164, "count": 63632, "is_parallel": true, "self": 25.06599376402164 }, "communicator.exchange": { "total": 1097.8595759569932, "count": 63632, "is_parallel": true, "self": 1097.8595759569932 }, "steps_from_proto": { "total": 102.07190989400806, "count": 63632, "is_parallel": true, "self": 20.634686201144177, "children": { "_process_rank_one_or_two_observation": { "total": 81.43722369286388, "count": 509056, "is_parallel": true, "self": 81.43722369286388 } } } } } } } } } } }, "trainer_advance": { "total": 618.0797340260096, "count": 63633, "self": 2.56983396301257, "children": { "process_trajectory": { "total": 127.16957141299213, "count": 63633, "self": 126.97594594199177, "children": { "RLTrainer._checkpoint": { "total": 0.19362547100035954, "count": 2, "self": 0.19362547100035954 } } }, "_update_policy": { "total": 488.34032865000495, "count": 451, "self": 287.08672804300136, "children": { "TorchPPOOptimizer.update": { "total": 201.2536006070036, "count": 22785, "self": 201.2536006070036 } } } } } } }, "trainer_threads": { "total": 9.70000201050425e-07, "count": 1, "self": 9.70000201050425e-07 }, "TrainerController._save_models": { "total": 0.08380197699989367, "count": 1, "self": 0.0013862689997949929, "children": { "RLTrainer._checkpoint": { "total": 0.08241570800009868, "count": 1, "self": 0.08241570800009868 } } } } } } }