{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4158954918384552, "min": 0.389771968126297, "max": 1.4734269380569458, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12589.98828125, "min": 11740.3193359375, "max": 44697.87890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49391746520996094, "min": -0.13662196695804596, "max": 0.49391746520996094, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.82730102539062, "min": -32.3794059753418, "max": 135.82730102539062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0580705851316452, "min": -0.0006240357179194689, "max": 0.30669668316841125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.96941089630127, "min": -0.16724157333374023, "max": 73.6072006225586, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0659523118076261, "min": 0.06214792239176244, "max": 0.07324698549012974, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9233323653067654, "min": 0.49948693167561425, "max": 1.0535105439873103, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014089648940484529, "min": 0.0012210792896699527, "max": 0.015995172932716305, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1972550851667834, "min": 0.008547555027689668, "max": 0.22393242105802827, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.459297513599999e-06, "min": 7.459297513599999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010443016519039999, "min": 0.00010443016519039999, "max": 0.0036323821892060002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024864, "min": 0.1024864, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348096000000001, "min": 1.3691136000000002, "max": 2.610794, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025839136, "min": 0.00025839136, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00361747904, "min": 0.00361747904, "max": 0.12109832059999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01364948321133852, "min": 0.01364948321133852, "max": 0.45635920763015747, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19109275937080383, "min": 0.19109275937080383, "max": 3.194514513015747, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.8125, "min": 392.8125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31425.0, "min": 15984.0, "max": 33455.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5323431876338558, "min": -1.0000000521540642, "max": 1.5323431876338558, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.11979819834232, "min": -32.000001668930054, "max": 124.11979819834232, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5323431876338558, "min": -1.0000000521540642, "max": 1.5323431876338558, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.11979819834232, "min": -32.000001668930054, "max": 124.11979819834232, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05513287935280931, "min": 0.05513287935280931, "max": 8.256304275244474, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.465763227577554, "min": 4.316449711099267, "max": 132.1008684039116, "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": "1677724614", "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": "1.22.4", "end_time_seconds": "1677726777" }, "total": 2163.240287427, "count": 1, "self": 0.4916142500001115, "children": { "run_training.setup": { "total": 0.13984603699998388, "count": 1, "self": 0.13984603699998388 }, "TrainerController.start_learning": { "total": 2162.60882714, "count": 1, "self": 1.3835908649507473, "children": { "TrainerController._reset_env": { "total": 8.95313700099996, "count": 1, "self": 8.95313700099996 }, "TrainerController.advance": { "total": 2152.1859800810494, "count": 63642, "self": 1.4566293830730501, "children": { "env_step": { "total": 1406.463887844993, "count": 63642, "self": 1295.2523270128995, "children": { "SubprocessEnvManager._take_step": { "total": 110.39384170203465, "count": 63642, "self": 4.646417592010835, "children": { "TorchPolicy.evaluate": { "total": 105.74742411002381, "count": 62552, "self": 35.834896240005946, "children": { "TorchPolicy.sample_actions": { "total": 69.91252787001787, "count": 62552, "self": 69.91252787001787 } } } } }, "workers": { "total": 0.8177191300587765, "count": 63642, "self": 0.0, "children": { "worker_root": { "total": 2158.0468960330263, "count": 63642, "is_parallel": true, "self": 976.3830133760409, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007566816000007748, "count": 1, "is_parallel": true, "self": 0.0036314160000188167, "children": { "_process_rank_one_or_two_observation": { "total": 0.003935399999988931, "count": 8, "is_parallel": true, "self": 0.003935399999988931 } } }, "UnityEnvironment.step": { "total": 0.04623834099999158, "count": 1, "is_parallel": true, "self": 0.0005233539999949244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046651200000269455, "count": 1, "is_parallel": true, "self": 0.00046651200000269455 }, "communicator.exchange": { "total": 0.04369535299997551, "count": 1, "is_parallel": true, "self": 0.04369535299997551 }, "steps_from_proto": { "total": 0.0015531220000184476, "count": 1, "is_parallel": true, "self": 0.00042028000018490275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011328419998335448, "count": 8, "is_parallel": true, "self": 0.0011328419998335448 } } } } } } }, "UnityEnvironment.step": { "total": 1181.6638826569854, "count": 63641, "is_parallel": true, "self": 31.008463282028515, "children": { "UnityEnvironment._generate_step_input": { "total": 22.46106564900731, "count": 63641, "is_parallel": true, "self": 22.46106564900731 }, "communicator.exchange": { "total": 1038.325666692962, "count": 63641, "is_parallel": true, "self": 1038.325666692962 }, "steps_from_proto": { "total": 89.8686870329878, "count": 63641, "is_parallel": true, "self": 21.205262208952092, "children": { "_process_rank_one_or_two_observation": { "total": 68.6634248240357, "count": 509128, "is_parallel": true, "self": 68.6634248240357 } } } } } } } } } } }, "trainer_advance": { "total": 744.2654628529833, "count": 63642, "self": 2.5519946449730924, "children": { "process_trajectory": { "total": 160.7506414150135, "count": 63642, "self": 160.5375760380137, "children": { "RLTrainer._checkpoint": { "total": 0.21306537699979344, "count": 2, "self": 0.21306537699979344 } } }, "_update_policy": { "total": 580.9628267929968, "count": 450, "self": 227.24300921802825, "children": { "TorchPPOOptimizer.update": { "total": 353.71981757496854, "count": 22833, "self": 353.71981757496854 } } } } } } }, "trainer_threads": { "total": 1.3939998098067008e-06, "count": 1, "self": 1.3939998098067008e-06 }, "TrainerController._save_models": { "total": 0.08611779900002148, "count": 1, "self": 0.001332176000232721, "children": { "RLTrainer._checkpoint": { "total": 0.08478562299978876, "count": 1, "self": 0.08478562299978876 } } } } } } }