{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40807926654815674, "min": 0.39849692583084106, "max": 1.566693663597107, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 8239.9365234375, "min": 7510.8701171875, "max": 37901.453125, "count": 50 }, "Pyramids.Step.mean": { "value": 999879.0, "min": 19968.0, "max": 999879.0, "count": 50 }, "Pyramids.Step.sum": { "value": 999879.0, "min": 19968.0, "max": 999879.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6960892677307129, "min": -0.1059286966919899, "max": 0.6960892677307129, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.04132080078125, "min": -16.939590454101562, "max": 135.04132080078125, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009455847553908825, "min": -8.2913160440512e-05, "max": 0.5536962747573853, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8344345092773438, "min": -0.014841455966234207, "max": 88.03771209716797, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.09802347963103991, "min": 0.09443996555179189, "max": 0.10476052000170426, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9802347963103991, "min": 0.7579609689070907, "max": 1.0287409441631703, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016610853364470164, "min": 0.0005056240712909006, "max": 0.019629756124710317, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16610853364470163, "min": 0.004044992570327205, "max": 0.19629756124710315, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.1994789335399998e-06, "min": 3.1994789335399998e-06, "max": 0.00029673000109, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.19947893354e-05, "min": 3.19947893354e-05, "max": 0.00237384000872, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10106646000000004, "min": 0.10106646000000004, "max": 0.19891000000000003, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.0106646000000004, "min": 0.9272891999999998, "max": 1.5912800000000002, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011653935400000003, "min": 0.00011653935400000003, "max": 0.009891108999999999, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0011653935400000003, "min": 0.0011653935400000003, "max": 0.07912887199999999, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0077946423552930355, "min": 0.0077946423552930355, "max": 0.7602221965789795, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07794642448425293, "min": 0.07089699804782867, "max": 6.081777572631836, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 265.12345679012344, "min": 244.1492537313433, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 21475.0, "min": 15013.0, "max": 30749.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7137544170210632, "min": -1.0000000521540642, "max": 1.7507999863227208, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 135.386598944664, "min": -28.778801642358303, "max": 135.386598944664, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7137544170210632, "min": -1.0000000521540642, "max": 1.7507999863227208, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 135.386598944664, "min": -28.778801642358303, "max": 135.386598944664, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0216094653923035, "min": 0.020925295427441596, "max": 10.618056608363986, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7071477659919765, "min": 1.5693971570581198, "max": 169.88890573382378, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739207647", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739210052" }, "total": 2405.6196106019997, "count": 1, "self": 0.5407556160002969, "children": { "run_training.setup": { "total": 0.022931064999738737, "count": 1, "self": 0.022931064999738737 }, "TrainerController.start_learning": { "total": 2405.0559239209997, "count": 1, "self": 2.621241670951804, "children": { "TrainerController._reset_env": { "total": 1.940776765999999, "count": 1, "self": 1.940776765999999 }, "TrainerController.advance": { "total": 2400.427822158047, "count": 64312, "self": 1.2881313299767498, "children": { "env_step": { "total": 2399.1396908280703, "count": 64312, "self": 2020.826398299855, "children": { "SubprocessEnvManager._take_step": { "total": 376.9672182560398, "count": 64312, "self": 6.703755859979992, "children": { "TorchPolicy.evaluate": { "total": 370.2634623960598, "count": 62617, "self": 370.2634623960598 } } }, "workers": { "total": 1.3460742721754286, "count": 64312, "self": 0.0, "children": { "worker_root": { "total": 2399.0555567319702, "count": 64312, "is_parallel": true, "self": 832.5007797619833, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002247566999812989, "count": 1, "is_parallel": true, "self": 0.0007598669999424601, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014876999998705287, "count": 8, "is_parallel": true, "self": 0.0014876999998705287 } } }, "UnityEnvironment.step": { "total": 0.053412011999625975, "count": 1, "is_parallel": true, "self": 0.0005670450000252458, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044411899989427184, "count": 1, "is_parallel": true, "self": 0.00044411899989427184 }, "communicator.exchange": { "total": 0.05067750199987131, "count": 1, "is_parallel": true, "self": 0.05067750199987131 }, "steps_from_proto": { "total": 0.0017233459998351464, "count": 1, "is_parallel": true, "self": 0.0003818439990936895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013415020007414569, "count": 8, "is_parallel": true, "self": 0.0013415020007414569 } } } } } } }, "UnityEnvironment.step": { "total": 1566.554776969987, "count": 64311, "is_parallel": true, "self": 35.33999374398536, "children": { "UnityEnvironment._generate_step_input": { "total": 23.15470984998683, "count": 64311, "is_parallel": true, "self": 23.15470984998683 }, "communicator.exchange": { "total": 1401.2888629349754, "count": 64311, "is_parallel": true, "self": 1401.2888629349754 }, "steps_from_proto": { "total": 106.77121044103933, "count": 64311, "is_parallel": true, "self": 23.716394777736696, "children": { "_process_rank_one_or_two_observation": { "total": 83.05481566330263, "count": 514488, "is_parallel": true, "self": 83.05481566330263 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0009279070000047795, "count": 1, "self": 0.0009279070000047795, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2402.9501970550114, "count": 11763, "is_parallel": true, "self": 0.3770159690179753, "children": { "process_trajectory": { "total": 435.172727861996, "count": 11763, "is_parallel": true, "self": 434.82782423299614, "children": { "RLTrainer._checkpoint": { "total": 0.34490362899987304, "count": 2, "is_parallel": true, "self": 0.34490362899987304 } } }, "_update_policy": { "total": 1967.4004532239974, "count": 441, "is_parallel": true, "self": 677.6209665349425, "children": { "TorchPPOOptimizer.update": { "total": 1289.779486689055, "count": 46242, "is_parallel": true, "self": 1289.779486689055 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0651554190008028, "count": 1, "self": 0.0009898250009428011, "children": { "RLTrainer._checkpoint": { "total": 0.06416559399986, "count": 1, "self": 0.06416559399986 } } } } } } }