{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0835151672363281, "min": 1.0835151672363281, "max": 1.5257622003555298, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 32453.4453125, "min": 32453.4453125, "max": 46285.5234375, "count": 3 }, "Pyramids.Step.mean": { "value": 89922.0, "min": 29952.0, "max": 89922.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89922.0, "min": 29952.0, "max": 89922.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08867810666561127, "min": -0.08867810666561127, "max": 0.07104282081127167, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.282745361328125, "min": -21.282745361328125, "max": 16.837148666381836, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1582680195569992, "min": 0.1582680195569992, "max": 0.4405379891395569, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 37.98432540893555, "min": 37.98432540893555, "max": 104.40750122070312, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06670783374719283, "min": 0.06670783374719283, "max": 0.0724487753318865, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6003705037247354, "min": 0.5071414273232054, "max": 0.6307520627593446, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00027809637314151506, "min": 0.00027809637314151506, "max": 0.010961821917419734, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0025028673582736354, "min": 0.0025028673582736354, "max": 0.07673275342193814, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.48634083788889e-05, "min": 7.48634083788889e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00067377067541, "min": 0.00067377067541, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12495444444444447, "min": 0.12495444444444447, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.1245900000000002, "min": 1.1245900000000002, "max": 1.3844619999999999, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.002502949, "min": 0.002502949, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.022526541, "min": 0.022526541, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.10466020554304123, "min": 0.10466020554304123, "max": 0.4057938754558563, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.9419418573379517, "min": 0.9419418573379517, "max": 2.840557098388672, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 997.0625, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31968.0, "min": 15984.0, "max": 31968.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.999987552408129, "min": -1.0000000521540642, "max": -0.9355313021223992, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -31.999601677060127, "min": -31.999601677060127, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.999987552408129, "min": -1.0000000521540642, "max": -0.9355313021223992, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -31.999601677060127, "min": -31.999601677060127, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.244899629149586, "min": 1.244899629149586, "max": 8.592460774816573, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 39.83678813278675, "min": 39.83678813278675, "max": 137.47937239706516, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676841282", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676841611" }, "total": 329.59086154199997, "count": 1, "self": 1.119241076000094, "children": { "run_training.setup": { "total": 0.16447067899991907, "count": 1, "self": 0.16447067899991907 }, "TrainerController.start_learning": { "total": 328.30714978699996, "count": 1, "self": 0.21547677499313522, "children": { "TrainerController._reset_env": { "total": 10.110676624000007, "count": 1, "self": 10.110676624000007 }, "TrainerController.advance": { "total": 317.7982026450069, "count": 6265, "self": 0.2609329820045332, "children": { "env_step": { "total": 183.20002682699226, "count": 6265, "self": 167.57378283698642, "children": { "SubprocessEnvManager._take_step": { "total": 15.480605588003414, "count": 6265, "self": 0.7204715160031583, "children": { "TorchPolicy.evaluate": { "total": 14.760134072000255, "count": 6260, "self": 3.161190493001641, "children": { "TorchPolicy.sample_actions": { "total": 11.598943578998615, "count": 6260, "self": 11.598943578998615 } } } } }, "workers": { "total": 0.14563840200241884, "count": 6265, "self": 0.0, "children": { "worker_root": { "total": 327.6130189869941, "count": 6265, "is_parallel": true, "self": 177.08064803098944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.011128786999961449, "count": 1, "is_parallel": true, "self": 0.006503035999912754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0046257510000486946, "count": 8, "is_parallel": true, "self": 0.0046257510000486946 } } }, "UnityEnvironment.step": { "total": 0.06914055199990798, "count": 1, "is_parallel": true, "self": 0.0006731079998871792, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007300669999494858, "count": 1, "is_parallel": true, "self": 0.0007300669999494858 }, "communicator.exchange": { "total": 0.06517923800004155, "count": 1, "is_parallel": true, "self": 0.06517923800004155 }, "steps_from_proto": { "total": 0.002558139000029769, "count": 1, "is_parallel": true, "self": 0.0007207170001493068, "children": { "_process_rank_one_or_two_observation": { "total": 0.001837421999880462, "count": 8, "is_parallel": true, "self": 0.001837421999880462 } } } } } } }, "UnityEnvironment.step": { "total": 150.53237095600468, "count": 6264, "is_parallel": true, "self": 4.607567904012171, "children": { "UnityEnvironment._generate_step_input": { "total": 2.605182551003054, "count": 6264, "is_parallel": true, "self": 2.605182551003054 }, "communicator.exchange": { "total": 130.09750493099386, "count": 6264, "is_parallel": true, "self": 130.09750493099386 }, "steps_from_proto": { "total": 13.222115569995594, "count": 6264, "is_parallel": true, "self": 3.22646498199947, "children": { "_process_rank_one_or_two_observation": { "total": 9.995650587996124, "count": 50112, "is_parallel": true, "self": 9.995650587996124 } } } } } } } } } } }, "trainer_advance": { "total": 134.3372428360101, "count": 6265, "self": 0.30902015800711524, "children": { "process_trajectory": { "total": 22.619742652002856, "count": 6265, "self": 22.619742652002856 }, "_update_policy": { "total": 111.40848002600012, "count": 29, "self": 28.880597093998063, "children": { "TorchPPOOptimizer.update": { "total": 82.52788293200206, "count": 2292, "self": 82.52788293200206 } } } } } } }, "trainer_threads": { "total": 1.991999965866853e-06, "count": 1, "self": 1.991999965866853e-06 }, "TrainerController._save_models": { "total": 0.18279175099996792, "count": 1, "self": 0.002382371999942734, "children": { "RLTrainer._checkpoint": { "total": 0.18040937900002518, "count": 1, "self": 0.18040937900002518 } } } } } } }