{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16093112528324127, "min": 0.14973129332065582, "max": 1.4687169790267944, "count": 73 }, "Pyramids.Policy.Entropy.sum": { "value": 4827.93359375, "min": 4465.5859375, "max": 44555.0, "count": 73 }, "Pyramids.Step.mean": { "value": 2189999.0, "min": 29952.0, "max": 2189999.0, "count": 73 }, "Pyramids.Step.sum": { "value": 2189999.0, "min": 29952.0, "max": 2189999.0, "count": 73 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7698275446891785, "min": -0.11906354874372482, "max": 0.8018506169319153, "count": 73 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 227.86895751953125, "min": -28.575252532958984, "max": 234.140380859375, "count": 73 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012321759946644306, "min": -0.008147596381604671, "max": 0.2541937530040741, "count": 73 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6472408771514893, "min": -2.1265225410461426, "max": 61.006500244140625, "count": 73 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07202943201090896, "min": 0.06555995500853493, "max": 0.07514585461059888, "count": 73 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0084120481527254, "min": 0.4884751299690541, "max": 1.0711755824935003, "count": 73 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01305162610792433, "min": 0.00018490804629228415, "max": 0.016653739772866376, "count": 73 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1827227655109406, "min": 0.0022188965555074098, "max": 0.24980609659299563, "count": 73 }, "Pyramids.Policy.LearningRate.mean": { "value": 8.245804394258094e-05, "min": 8.245804394258094e-05, "max": 0.00029838354339596195, "count": 73 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0011544126151961332, "min": 0.0011544126151961332, "max": 0.004027430757523133, "count": 73 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1274859904761905, "min": 0.1274859904761905, "max": 0.19946118095238097, "count": 73 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.7848038666666668, "min": 1.3897045333333333, "max": 2.842476866666667, "count": 73 }, "Pyramids.Policy.Beta.mean": { "value": 0.0027558504485714294, "min": 0.0027558504485714294, "max": 0.009946171977142856, "count": 73 }, "Pyramids.Policy.Beta.sum": { "value": 0.03858190628000001, "min": 0.03858190628000001, "max": 0.13426343898, "count": 73 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008542558178305626, "min": 0.00810875091701746, "max": 0.34159430861473083, "count": 73 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11959581822156906, "min": 0.11352250725030899, "max": 2.391160249710083, "count": 73 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 238.94827586206895, "min": 237.88429752066116, "max": 999.0, "count": 73 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27718.0, "min": 15984.0, "max": 34345.0, "count": 73 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7265517061640476, "min": -1.0000000521540642, "max": 1.7469649847596884, "count": 73 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 200.27999791502953, "min": -32.000001668930054, "max": 215.98819863796234, "count": 73 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7265517061640476, "min": -1.0000000521540642, "max": 1.7469649847596884, "count": 73 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 200.27999791502953, "min": -32.000001668930054, "max": 215.98819863796234, "count": 73 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02134822721012009, "min": 0.021039137857709042, "max": 6.199004173278809, "count": 73 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4763943563739303, "min": 2.4763943563739303, "max": 99.18406677246094, "count": 73 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 73 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 73 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1777362201", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1777367616" }, "total": 5414.665922715, "count": 1, "self": 0.3932694530003573, "children": { "run_training.setup": { "total": 0.02395800399995096, "count": 1, "self": 0.02395800399995096 }, "TrainerController.start_learning": { "total": 5414.248695258, "count": 1, "self": 3.3579498651433823, "children": { "TrainerController._reset_env": { "total": 2.982527981000203, "count": 1, "self": 2.982527981000203 }, "TrainerController.advance": { "total": 5407.718882891856, "count": 143167, "self": 3.4943771617954553, "children": { "env_step": { "total": 3898.51154172517, "count": 143167, "self": 3539.6839358451025, "children": { "SubprocessEnvManager._take_step": { "total": 356.768004589165, "count": 143167, "self": 10.675336042209892, "children": { "TorchPolicy.evaluate": { "total": 346.0926685469551, "count": 138456, "self": 346.0926685469551 } } }, "workers": { "total": 2.0596012909022647, "count": 143167, "self": 0.0, "children": { "worker_root": { "total": 5397.7861618759935, "count": 143167, "is_parallel": true, "self": 2136.8680878639325, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024737400001413334, "count": 1, "is_parallel": true, "self": 0.0007250270002714387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017487129998698947, "count": 8, "is_parallel": true, "self": 0.0017487129998698947 } } }, "UnityEnvironment.step": { "total": 0.07875738300003832, "count": 1, "is_parallel": true, "self": 0.0006336239998745441, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0016093780000119295, "count": 1, "is_parallel": true, "self": 0.0016093780000119295 }, "communicator.exchange": { "total": 0.0745510760000343, "count": 1, "is_parallel": true, "self": 0.0745510760000343 }, "steps_from_proto": { "total": 0.0019633050001175434, "count": 1, "is_parallel": true, "self": 0.0005785980001746793, "children": { "_process_rank_one_or_two_observation": { "total": 0.001384706999942864, "count": 8, "is_parallel": true, "self": 0.001384706999942864 } } } } } } }, "UnityEnvironment.step": { "total": 3260.918074012061, "count": 143166, "is_parallel": true, "self": 77.39514849019542, "children": { "UnityEnvironment._generate_step_input": { "total": 53.32608670487957, "count": 143166, "is_parallel": true, "self": 53.32608670487957 }, "communicator.exchange": { "total": 2877.7350703080283, "count": 143166, "is_parallel": true, "self": 2877.7350703080283 }, "steps_from_proto": { "total": 252.4617685089579, "count": 143166, "is_parallel": true, "self": 53.73386885277728, "children": { "_process_rank_one_or_two_observation": { "total": 198.72789965618063, "count": 1145328, "is_parallel": true, "self": 198.72789965618063 } } } } } } } } } } }, "trainer_advance": { "total": 1505.7129640048902, "count": 143167, "self": 6.665443870746458, "children": { "process_trajectory": { "total": 288.9727525321432, "count": 143167, "self": 288.6280877711433, "children": { "RLTrainer._checkpoint": { "total": 0.3446647609998763, "count": 4, "self": 0.3446647609998763 } } }, "_update_policy": { "total": 1210.0747676020005, "count": 1023, "self": 669.363920580183, "children": { "TorchPPOOptimizer.update": { "total": 540.7108470218175, "count": 50478, "self": 540.7108470218175 } } } } } } }, "trainer_threads": { "total": 1.4960005501052365e-06, "count": 1, "self": 1.4960005501052365e-06 }, "TrainerController._save_models": { "total": 0.18933302400000684, "count": 1, "self": 0.0013314219995663734, "children": { "RLTrainer._checkpoint": { "total": 0.18800160200044047, "count": 1, "self": 0.18800160200044047 } } } } } } }