{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20595188438892365, "min": 0.20595188438892365, "max": 1.5710982084274292, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6221.39453125, "min": 6221.39453125, "max": 50275.14453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29912.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29912.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 1.048952341079712, "min": -0.07387077808380127, "max": 1.1315163373947144, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.88133239746094, "min": -8.864493370056152, "max": 201.12667846679688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02207227423787117, "min": 0.015805792063474655, "max": 1.1288546323776245, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.553636074066162, "min": 2.7185962200164795, "max": 135.46255493164062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.046727997723272505, "min": 0.045684902510402026, "max": 0.053374530114282004, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3270959840629075, "min": 0.160123590342846, "max": 0.39834777383721837, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010151146877823132, "min": 0.0032943747048314737, "max": 0.04713826015176892, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07105802814476192, "min": 0.01647187352415737, "max": 0.14141478045530675, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.738511706242858e-06, "min": 7.738511706242858e-06, "max": 0.00029516160161279994, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.416958194370001e-05, "min": 5.416958194370001e-05, "max": 0.0019443117518961003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257947142857145, "min": 0.10257947142857145, "max": 0.19838719999999999, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7180563000000001, "min": 0.5951616, "max": 1.3721094000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00013871562428571433, "min": 0.00013871562428571433, "max": 0.004919521280000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009710093700000003, "min": 0.0009710093700000003, "max": 0.03241038461, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02559191919863224, "min": 0.02559191919863224, "max": 0.7204501032829285, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17914342880249023, "min": 0.17914342880249023, "max": 2.1613502502441406, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 275.75471698113205, "min": 234.03968253968253, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29230.0, "min": 17162.0, "max": 34168.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.62987356675121, "min": -1.0000000596046448, "max": 1.7487086442511852, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 172.76659807562828, "min": -23.00000137090683, "max": 222.0859978199005, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.62987356675121, "min": -1.0000000596046448, "max": 1.7487086442511852, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 172.76659807562828, "min": -23.00000137090683, "max": 222.0859978199005, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14667406935851038, "min": 0.13154307487122932, "max": 28.92618169473565, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 15.5474513520021, "min": 15.5474513520021, "max": 665.30217897892, "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": "1775184648", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/opt/conda/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1775188389" }, "total": 3741.028210996, "count": 1, "self": 0.9038767869997173, "children": { "run_training.setup": { "total": 0.028557712000292668, "count": 1, "self": 0.028557712000292668 }, "TrainerController.start_learning": { "total": 3740.095776497, "count": 1, "self": 2.2121643868849787, "children": { "TrainerController._reset_env": { "total": 2.62472892400001, "count": 1, "self": 2.62472892400001 }, "TrainerController.advance": { "total": 3735.092350077114, "count": 64807, "self": 2.307653624330669, "children": { "env_step": { "total": 2347.3525503688243, "count": 64807, "self": 2162.596484293814, "children": { "SubprocessEnvManager._take_step": { "total": 183.36812177793945, "count": 64807, "self": 6.494025983868596, "children": { "TorchPolicy.evaluate": { "total": 176.87409579407085, "count": 62594, "self": 176.87409579407085 } } }, "workers": { "total": 1.3879442970710443, "count": 64807, "self": 0.0, "children": { "worker_root": { "total": 3731.3887510771174, "count": 64807, "is_parallel": true, "self": 1744.357965035062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019899709996025194, "count": 1, "is_parallel": true, "self": 0.000665481999021722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013244890005807974, "count": 8, "is_parallel": true, "self": 0.0013244890005807974 } } }, "UnityEnvironment.step": { "total": 0.1303035329992781, "count": 1, "is_parallel": true, "self": 0.0006033829986336059, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047354799971799366, "count": 1, "is_parallel": true, "self": 0.00047354799971799366 }, "communicator.exchange": { "total": 0.1254200800003673, "count": 1, "is_parallel": true, "self": 0.1254200800003673 }, "steps_from_proto": { "total": 0.003806522000559198, "count": 1, "is_parallel": true, "self": 0.0023788139997122926, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014277080008469056, "count": 8, "is_parallel": true, "self": 0.0014277080008469056 } } } } } } }, "UnityEnvironment.step": { "total": 1987.0307860420553, "count": 64806, "is_parallel": true, "self": 43.73144986220632, "children": { "UnityEnvironment._generate_step_input": { "total": 30.11174114698406, "count": 64806, "is_parallel": true, "self": 30.11174114698406 }, "communicator.exchange": { "total": 1773.0571450459447, "count": 64806, "is_parallel": true, "self": 1773.0571450459447 }, "steps_from_proto": { "total": 140.1304499869202, "count": 64806, "is_parallel": true, "self": 29.172332515341623, "children": { "_process_rank_one_or_two_observation": { "total": 110.95811747157859, "count": 518448, "is_parallel": true, "self": 110.95811747157859 } } } } } } } } } } }, "trainer_advance": { "total": 1385.4321460839592, "count": 64807, "self": 4.645751960623784, "children": { "process_trajectory": { "total": 166.11152387133916, "count": 64807, "self": 165.7449175433394, "children": { "RLTrainer._checkpoint": { "total": 0.36660632799976156, "count": 2, "self": 0.36660632799976156 } } }, "_update_policy": { "total": 1214.6748702519963, "count": 231, "self": 436.9255900480439, "children": { "TorchPPOOptimizer.update": { "total": 777.7492802039524, "count": 15188, "self": 777.7492802039524 } } } } } } }, "trainer_threads": { "total": 1.0109997674589977e-06, "count": 1, "self": 1.0109997674589977e-06 }, "TrainerController._save_models": { "total": 0.16653209800097102, "count": 1, "self": 0.01195176600231207, "children": { "RLTrainer._checkpoint": { "total": 0.15458033199865895, "count": 1, "self": 0.15458033199865895 } } } } } } }