{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15419963002204895, "min": 0.1439506560564041, "max": 1.4417672157287598, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4613.65283203125, "min": 4346.158203125, "max": 43737.44921875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999915.0, "min": 29981.0, "max": 2999915.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999915.0, "min": 29981.0, "max": 2999915.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7366708517074585, "min": -0.09642678499221802, "max": 0.8856813311576843, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 218.05458068847656, "min": -23.238855361938477, "max": 273.675537109375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015807395800948143, "min": -0.010172320529818535, "max": 0.30925413966178894, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.678989410400391, "min": -3.0008344650268555, "max": 74.22099304199219, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06624905925751332, "min": 0.06455514475306874, "max": 0.07447222975038346, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9274868296051865, "min": 0.5029721026285083, "max": 1.0506878335875753, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015946684902744545, "min": 9.625917285858086e-05, "max": 0.017056086639751725, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22325358863842362, "min": 0.0012513692471615512, "max": 0.2535860696904516, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.569978048135712e-06, "min": 1.569978048135712e-06, "max": 0.0002984123862434905, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.197969267389997e-05, "min": 2.197969267389997e-05, "max": 0.0037590180469940326, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052329285714286, "min": 0.10052329285714286, "max": 0.19947079523809524, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073261, "min": 1.3962955666666668, "max": 2.7075139666666663, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.227695642857136e-05, "min": 6.227695642857136e-05, "max": 0.009947132444285713, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008718773899999992, "min": 0.0008718773899999992, "max": 0.12531529607000003, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005896520335227251, "min": 0.005484605673700571, "max": 0.5323460698127747, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08255128562450409, "min": 0.07884299755096436, "max": 3.7264225482940674, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 249.256, "min": 208.79591836734693, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31157.0, "min": 16652.0, "max": 33642.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7012999837076472, "min": -1.0000000521540642, "max": 1.790217672278281, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 210.96119797974825, "min": -32.000001668930054, "max": 263.1619978249073, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7012999837076472, "min": -1.0000000521540642, "max": 1.790217672278281, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 210.96119797974825, "min": -32.000001668930054, "max": 263.1619978249073, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015280251960575697, "min": 0.012767925405061921, "max": 10.269266018534408, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8947512431113864, "min": 1.6837215152481804, "max": 174.57752231508493, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701961697", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701969641" }, "total": 7943.532301667, "count": 1, "self": 0.48971800099934626, "children": { "run_training.setup": { "total": 0.062130511000077604, "count": 1, "self": 0.062130511000077604 }, "TrainerController.start_learning": { "total": 7942.980453155001, "count": 1, "self": 4.816256082775908, "children": { "TrainerController._reset_env": { "total": 3.683077721000018, "count": 1, "self": 3.683077721000018 }, "TrainerController.advance": { "total": 7934.400853264224, "count": 194913, "self": 4.914871119586678, "children": { "env_step": { "total": 5924.135419012621, "count": 194913, "self": 5491.758064252891, "children": { "SubprocessEnvManager._take_step": { "total": 429.4342939949072, "count": 194913, "self": 15.616328825285791, "children": { "TorchPolicy.evaluate": { "total": 413.8179651696214, "count": 187549, "self": 413.8179651696214 } } }, "workers": { "total": 2.9430607648228033, "count": 194913, "self": 0.0, "children": { "worker_root": { "total": 7926.968700177998, "count": 194913, "is_parallel": true, "self": 2841.870881891001, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005556724999905782, "count": 1, "is_parallel": true, "self": 0.004163067999911618, "children": { "_process_rank_one_or_two_observation": { "total": 0.001393656999994164, "count": 8, "is_parallel": true, "self": 0.001393656999994164 } } }, "UnityEnvironment.step": { "total": 0.05895132599994213, "count": 1, "is_parallel": true, "self": 0.0006423359999416789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006649890000289815, "count": 1, "is_parallel": true, "self": 0.0006649890000289815 }, "communicator.exchange": { "total": 0.055636560000039026, "count": 1, "is_parallel": true, "self": 0.055636560000039026 }, "steps_from_proto": { "total": 0.0020074409999324416, "count": 1, "is_parallel": true, "self": 0.00042908799980523327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015783530001272084, "count": 8, "is_parallel": true, "self": 0.0015783530001272084 } } } } } } }, "UnityEnvironment.step": { "total": 5085.097818286997, "count": 194912, "is_parallel": true, "self": 110.48581408493192, "children": { "UnityEnvironment._generate_step_input": { "total": 78.84881484473817, "count": 194912, "is_parallel": true, "self": 78.84881484473817 }, "communicator.exchange": { "total": 4569.461790351076, "count": 194912, "is_parallel": true, "self": 4569.461790351076 }, "steps_from_proto": { "total": 326.30139900625, "count": 194912, "is_parallel": true, "self": 67.58338236588793, "children": { "_process_rank_one_or_two_observation": { "total": 258.71801664036207, "count": 1559296, "is_parallel": true, "self": 258.71801664036207 } } } } } } } } } } }, "trainer_advance": { "total": 2005.3505631320158, "count": 194913, "self": 9.425250947861969, "children": { "process_trajectory": { "total": 421.5178631541594, "count": 194913, "self": 420.97843281115865, "children": { "RLTrainer._checkpoint": { "total": 0.5394303430007312, "count": 6, "self": 0.5394303430007312 } } }, "_update_policy": { "total": 1574.4074490299945, "count": 1395, "self": 951.871964159049, "children": { "TorchPPOOptimizer.update": { "total": 622.5354848709455, "count": 68373, "self": 622.5354848709455 } } } } } } }, "trainer_threads": { "total": 8.620008884463459e-07, "count": 1, "self": 8.620008884463459e-07 }, "TrainerController._save_models": { "total": 0.080265225000403, "count": 1, "self": 0.0014251680004235823, "children": { "RLTrainer._checkpoint": { "total": 0.07884005699997942, "count": 1, "self": 0.07884005699997942 } } } } } } }