{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6310732364654541, "min": 0.6310732364654541, "max": 1.3959141969680786, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18952.390625, "min": 18952.390625, "max": 42346.453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.032886993139982224, "min": -0.11363182961940765, "max": 0.14573942124843597, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 8.090200424194336, "min": -26.930744171142578, "max": 36.58059310913086, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012540374882519245, "min": -0.008996750228106976, "max": 0.37704503536224365, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.084932327270508, "min": -2.2581841945648193, "max": 89.35967254638672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07299235814605796, "min": 0.0663074805212213, "max": 0.07392256023000274, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0218930140448115, "min": 0.47847403233687535, "max": 1.1073005621523513, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005172306961840684, "min": 7.009385213736068e-05, "max": 0.008751396156690638, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07241229746576958, "min": 0.0009813139299230495, "max": 0.13127094235035958, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.294983282657142e-06, "min": 7.294983282657142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001021297659572, "min": 0.0001021297659572, "max": 0.0035079632306789996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243162857142858, "min": 0.10243162857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340428, "min": 1.3886848, "max": 2.569321, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025291969428571436, "min": 0.00025291969428571436, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003540875720000001, "min": 0.003540875720000001, "max": 0.1169551679, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006385961081832647, "min": 0.006385961081832647, "max": 0.41979971528053284, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08940345793962479, "min": 0.08940345793962479, "max": 2.9385979175567627, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 790.6944444444445, "min": 699.5714285714286, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28465.0, "min": 15984.0, "max": 33141.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.20904995728698042, "min": -1.0000000521540642, "max": 0.6335571007359595, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 7.525798462331295, "min": -31.998801663517952, "max": 26.6093982309103, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.20904995728698042, "min": -1.0000000521540642, "max": 0.6335571007359595, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 7.525798462331295, "min": -31.998801663517952, "max": 26.6093982309103, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.052445290076623984, "min": 0.05149908337487085, "max": 8.643005074933171, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8880304427584633, "min": 1.8880304427584633, "max": 138.28808119893074, "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": "1710191480", "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": "1710194531" }, "total": 3050.9345805410003, "count": 1, "self": 1.0403221040000972, "children": { "run_training.setup": { "total": 0.06504595500001642, "count": 1, "self": 0.06504595500001642 }, "TrainerController.start_learning": { "total": 3049.829212482, "count": 1, "self": 2.230497359996207, "children": { "TrainerController._reset_env": { "total": 3.059294367999996, "count": 1, "self": 3.059294367999996 }, "TrainerController.advance": { "total": 3044.394948254004, "count": 63232, "self": 2.485702009943452, "children": { "env_step": { "total": 1999.5822363420393, "count": 63232, "self": 1843.661012953981, "children": { "SubprocessEnvManager._take_step": { "total": 154.53515758499776, "count": 63232, "self": 6.838763572977484, "children": { "TorchPolicy.evaluate": { "total": 147.69639401202028, "count": 62562, "self": 147.69639401202028 } } }, "workers": { "total": 1.3860658030604327, "count": 63232, "self": 0.0, "children": { "worker_root": { "total": 3043.761343642002, "count": 63232, "is_parallel": true, "self": 1379.3353660060393, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0057007320000366235, "count": 1, "is_parallel": true, "self": 0.003970366999965336, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017303650000712878, "count": 8, "is_parallel": true, "self": 0.0017303650000712878 } } }, "UnityEnvironment.step": { "total": 0.09822481600002675, "count": 1, "is_parallel": true, "self": 0.0007344379999949524, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004952660000299147, "count": 1, "is_parallel": true, "self": 0.0004952660000299147 }, "communicator.exchange": { "total": 0.09512028500000724, "count": 1, "is_parallel": true, "self": 0.09512028500000724 }, "steps_from_proto": { "total": 0.0018748269999946388, "count": 1, "is_parallel": true, "self": 0.00038232200006405037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014925049999305884, "count": 8, "is_parallel": true, "self": 0.0014925049999305884 } } } } } } }, "UnityEnvironment.step": { "total": 1664.4259776359627, "count": 63231, "is_parallel": true, "self": 50.12638596799343, "children": { "UnityEnvironment._generate_step_input": { "total": 28.3000757210325, "count": 63231, "is_parallel": true, "self": 28.3000757210325 }, "communicator.exchange": { "total": 1457.3324657969724, "count": 63231, "is_parallel": true, "self": 1457.3324657969724 }, "steps_from_proto": { "total": 128.66705014996444, "count": 63231, "is_parallel": true, "self": 27.291105369009642, "children": { "_process_rank_one_or_two_observation": { "total": 101.3759447809548, "count": 505848, "is_parallel": true, "self": 101.3759447809548 } } } } } } } } } } }, "trainer_advance": { "total": 1042.327009902021, "count": 63232, "self": 4.468622044008725, "children": { "process_trajectory": { "total": 157.63803292100351, "count": 63232, "self": 157.36351337500332, "children": { "RLTrainer._checkpoint": { "total": 0.27451954600019235, "count": 2, "self": 0.27451954600019235 } } }, "_update_policy": { "total": 880.2203549370088, "count": 444, "self": 363.4256263960556, "children": { "TorchPPOOptimizer.update": { "total": 516.7947285409532, "count": 22779, "self": 516.7947285409532 } } } } } } }, "trainer_threads": { "total": 1.3829999261361081e-06, "count": 1, "self": 1.3829999261361081e-06 }, "TrainerController._save_models": { "total": 0.14447111700019377, "count": 1, "self": 0.0031317930001932837, "children": { "RLTrainer._checkpoint": { "total": 0.1413393240000005, "count": 1, "self": 0.1413393240000005 } } } } } } }