{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47815948724746704, "min": 0.47815948724746704, "max": 1.4071797132492065, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 14291.23046875, "min": 14291.23046875, "max": 42688.203125, "count": 36 }, "Pyramids.Step.mean": { "value": 1079945.0, "min": 29952.0, "max": 1079945.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079945.0, "min": 29952.0, "max": 1079945.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6419244408607483, "min": -0.11252445727586746, "max": 0.6419244408607483, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 179.7388458251953, "min": -27.230918884277344, "max": 180.59671020507812, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.010029821656644344, "min": -0.010826490819454193, "max": 0.49480146169662476, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.808350086212158, "min": -2.8798465728759766, "max": 117.2679443359375, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06839069515644085, "min": 0.06356442188067982, "max": 0.07343371467483369, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9574697321901718, "min": 0.500739667878082, "max": 1.090445691855469, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014643920549826274, "min": 0.0005605292232609406, "max": 0.014891801925495244, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20501488769756784, "min": 0.007847409125653168, "max": 0.2166041955545855, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001935294854901833, "min": 0.0001935294854901833, "max": 0.00029838354339596195, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027094127968625664, "min": 0.0020886848037717336, "max": 0.004010992663002467, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16450981666666667, "min": 0.16450981666666667, "max": 0.19946118095238097, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.303137433333333, "min": 1.3962282666666668, "max": 2.737553433333334, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.006454530685, "min": 0.006454530685, "max": 0.009946171977142856, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.09036342959, "min": 0.06962320384, "max": 0.13370605358, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009860126301646233, "min": 0.008886665105819702, "max": 0.4953594505786896, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13804176449775696, "min": 0.12441331148147583, "max": 3.4675161838531494, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.3, "min": 292.43564356435644, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28107.0, "min": 15984.0, "max": 32703.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6210066413713826, "min": -1.0000000521540642, "max": 1.6210066413713826, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.89059772342443, "min": -29.163801692426205, "max": 162.46159832179546, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6210066413713826, "min": -1.0000000521540642, "max": 1.6210066413713826, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.89059772342443, "min": -29.163801692426205, "max": 162.46159832179546, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03258738735959115, "min": 0.030348350527341302, "max": 10.07096153870225, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9328648623632034, "min": 2.7411322458283394, "max": 161.135384619236, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711385354", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711387896" }, "total": 2542.346151972, "count": 1, "self": 0.5309858070004339, "children": { "run_training.setup": { "total": 0.051982106999730604, "count": 1, "self": 0.051982106999730604 }, "TrainerController.start_learning": { "total": 2541.7631840579998, "count": 1, "self": 1.7213359299171316, "children": { "TrainerController._reset_env": { "total": 2.2638276279999445, "count": 1, "self": 2.2638276279999445 }, "TrainerController.advance": { "total": 2537.7780191400834, "count": 70343, "self": 1.8593174349753099, "children": { "env_step": { "total": 1832.1659136910534, "count": 70343, "self": 1671.802882216141, "children": { "SubprocessEnvManager._take_step": { "total": 159.29616255194878, "count": 70343, "self": 5.766553772971747, "children": { "TorchPolicy.evaluate": { "total": 153.52960877897704, "count": 68888, "self": 153.52960877897704 } } }, "workers": { "total": 1.0668689229637494, "count": 70342, "self": 0.0, "children": { "worker_root": { "total": 2535.909101165019, "count": 70342, "is_parallel": true, "self": 1010.0970267519479, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002364308999858622, "count": 1, "is_parallel": true, "self": 0.0007468940002581803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016174149996004417, "count": 8, "is_parallel": true, "self": 0.0016174149996004417 } } }, "UnityEnvironment.step": { "total": 0.08976130900009593, "count": 1, "is_parallel": true, "self": 0.0006464590001087345, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004880199999206525, "count": 1, "is_parallel": true, "self": 0.0004880199999206525 }, "communicator.exchange": { "total": 0.08697422899967933, "count": 1, "is_parallel": true, "self": 0.08697422899967933 }, "steps_from_proto": { "total": 0.0016526010003872216, "count": 1, "is_parallel": true, "self": 0.00032361900002797483, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013289820003592467, "count": 8, "is_parallel": true, "self": 0.0013289820003592467 } } } } } } }, "UnityEnvironment.step": { "total": 1525.812074413071, "count": 70341, "is_parallel": true, "self": 40.40756634888703, "children": { "UnityEnvironment._generate_step_input": { "total": 28.177959748069952, "count": 70341, "is_parallel": true, "self": 28.177959748069952 }, "communicator.exchange": { "total": 1336.9210302860288, "count": 70341, "is_parallel": true, "self": 1336.9210302860288 }, "steps_from_proto": { "total": 120.3055180300853, "count": 70341, "is_parallel": true, "self": 25.02236169707021, "children": { "_process_rank_one_or_two_observation": { "total": 95.28315633301509, "count": 562728, "is_parallel": true, "self": 95.28315633301509 } } } } } } } } } } }, "trainer_advance": { "total": 703.7527880140547, "count": 70342, "self": 3.2670534280186985, "children": { "process_trajectory": { "total": 148.5039861730279, "count": 70342, "self": 148.2440870410278, "children": { "RLTrainer._checkpoint": { "total": 0.2598991320001005, "count": 2, "self": 0.2598991320001005 } } }, "_update_policy": { "total": 551.9817484130081, "count": 500, "self": 320.7032374350101, "children": { "TorchPPOOptimizer.update": { "total": 231.27851097799794, "count": 25053, "self": 231.27851097799794 } } } } } } }, "trainer_threads": { "total": 1.3599992598756216e-06, "count": 1, "self": 1.3599992598756216e-06 } } } } }