{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3967891335487366, "min": 0.3967891335487366, "max": 1.4358166456222534, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11878.279296875, "min": 11878.279296875, "max": 43556.93359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6713936924934387, "min": -0.10962054133415222, "max": 0.6713936924934387, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 192.6899871826172, "min": -26.308929443359375, "max": 192.6899871826172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01450098492205143, "min": -0.0021236592438071966, "max": 0.5306307673454285, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.161782741546631, "min": -0.5882536172866821, "max": 125.75949096679688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07087349866855046, "min": 0.06583802531568231, "max": 0.07485722266819958, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9922289813597065, "min": 0.4769274115140266, "max": 1.0564026535333444, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01551307074121377, "min": 0.0010077559598247097, "max": 0.016833744834487636, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21718299037699276, "min": 0.013284038919730325, "max": 0.25250617251731455, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.67137601433572e-06, "min": 7.67137601433572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010739926420070006, "min": 0.00010739926420070006, "max": 0.0036324157891947993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255709285714287, "min": 0.10255709285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357993000000002, "min": 1.3691136000000002, "max": 2.6108052, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026545357642857156, "min": 0.00026545357642857156, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003716350070000002, "min": 0.003716350070000002, "max": 0.12109943948000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009402148425579071, "min": 0.009402148425579071, "max": 0.5152145028114319, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.131630077958107, "min": 0.131630077958107, "max": 3.606501579284668, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 283.5, "min": 283.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30051.0, "min": 15984.0, "max": 33663.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.698175688213277, "min": -1.0000000521540642, "max": 1.698175688213277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.70479863882065, "min": -32.000001668930054, "max": 181.70479863882065, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.698175688213277, "min": -1.0000000521540642, "max": 1.698175688213277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.70479863882065, "min": -32.000001668930054, "max": 181.70479863882065, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02777701260819302, "min": 0.02777701260819302, "max": 10.795980498194695, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9721403490766534, "min": 2.9547697921516374, "max": 172.7356879711151, "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": "1681873837", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681876104" }, "total": 2267.0317817550003, "count": 1, "self": 0.5003556690007827, "children": { "run_training.setup": { "total": 0.10431657299977815, "count": 1, "self": 0.10431657299977815 }, "TrainerController.start_learning": { "total": 2266.427109513, "count": 1, "self": 1.2840382789868272, "children": { "TrainerController._reset_env": { "total": 4.244039212000189, "count": 1, "self": 4.244039212000189 }, "TrainerController.advance": { "total": 2260.8059180670125, "count": 64033, "self": 1.2858251449401905, "children": { "env_step": { "total": 1659.4850468309764, "count": 64033, "self": 1559.2506047948596, "children": { "SubprocessEnvManager._take_step": { "total": 99.47350274606697, "count": 64033, "self": 4.495202162888745, "children": { "TorchPolicy.evaluate": { "total": 94.97830058317822, "count": 62568, "self": 94.97830058317822 } } }, "workers": { "total": 0.7609392900499188, "count": 64033, "self": 0.0, "children": { "worker_root": { "total": 2261.2932821408795, "count": 64033, "is_parallel": true, "self": 808.5087569738971, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017822350000642473, "count": 1, "is_parallel": true, "self": 0.0005452790005620045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012369559995022428, "count": 8, "is_parallel": true, "self": 0.0012369559995022428 } } }, "UnityEnvironment.step": { "total": 0.11973106999994343, "count": 1, "is_parallel": true, "self": 0.007402935999380134, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004862949999733246, "count": 1, "is_parallel": true, "self": 0.0004862949999733246 }, "communicator.exchange": { "total": 0.10995105900019553, "count": 1, "is_parallel": true, "self": 0.10995105900019553 }, "steps_from_proto": { "total": 0.001890780000394443, "count": 1, "is_parallel": true, "self": 0.00035859400077242753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015321859996220155, "count": 8, "is_parallel": true, "self": 0.0015321859996220155 } } } } } } }, "UnityEnvironment.step": { "total": 1452.7845251669823, "count": 64032, "is_parallel": true, "self": 31.485309770095228, "children": { "UnityEnvironment._generate_step_input": { "total": 22.469902618941887, "count": 64032, "is_parallel": true, "self": 22.469902618941887 }, "communicator.exchange": { "total": 1307.1010758040175, "count": 64032, "is_parallel": true, "self": 1307.1010758040175 }, "steps_from_proto": { "total": 91.72823697392778, "count": 64032, "is_parallel": true, "self": 19.111396844788032, "children": { "_process_rank_one_or_two_observation": { "total": 72.61684012913975, "count": 512256, "is_parallel": true, "self": 72.61684012913975 } } } } } } } } } } }, "trainer_advance": { "total": 600.0350460910959, "count": 64033, "self": 2.300495330065587, "children": { "process_trajectory": { "total": 102.73022515203274, "count": 64033, "self": 102.52198539103301, "children": { "RLTrainer._checkpoint": { "total": 0.20823976099973152, "count": 2, "self": 0.20823976099973152 } } }, "_update_policy": { "total": 495.00432560899753, "count": 447, "self": 315.0499840500256, "children": { "TorchPPOOptimizer.update": { "total": 179.95434155897192, "count": 22851, "self": 179.95434155897192 } } } } } } }, "trainer_threads": { "total": 8.639999578008428e-07, "count": 1, "self": 8.639999578008428e-07 }, "TrainerController._save_models": { "total": 0.09311309100030485, "count": 1, "self": 0.001703812000414473, "children": { "RLTrainer._checkpoint": { "total": 0.09140927899989038, "count": 1, "self": 0.09140927899989038 } } } } } } }