{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34482669830322266, "min": 0.34482669830322266, "max": 1.4624285697937012, "count": 37 }, "Pyramids.Policy.Entropy.sum": { "value": 10344.80078125, "min": 10344.80078125, "max": 44364.234375, "count": 37 }, "Pyramids.Step.mean": { "value": 1109901.0, "min": 29952.0, "max": 1109901.0, "count": 37 }, "Pyramids.Step.sum": { "value": 1109901.0, "min": 29952.0, "max": 1109901.0, "count": 37 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6680407524108887, "min": -0.15676526725292206, "max": 0.7045049667358398, "count": 37 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 189.72357177734375, "min": -37.15336990356445, "max": 202.89743041992188, "count": 37 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010759801603853703, "min": 0.0036925566382706165, "max": 0.39287158846855164, "count": 37 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.055783748626709, "min": 0.9526796340942383, "max": 93.11056518554688, "count": 37 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07033778849983632, "min": 0.06535702866044923, "max": 0.07368001354735777, "count": 37 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9847290389977086, "min": 0.512197334549173, "max": 1.1052002032103665, "count": 37 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015167649777140468, "min": 0.0013843536278094065, "max": 0.016498862148027118, "count": 37 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21234709687996656, "min": 0.01938095078933169, "max": 0.23098407007237967, "count": 37 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019047644365072144, "min": 0.00019047644365072144, "max": 0.00029838354339596195, "count": 37 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0026666702111101, "min": 0.0020886848037717336, "max": 0.004010746163084633, "count": 37 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16349213571428572, "min": 0.16349213571428572, "max": 0.19946118095238097, "count": 37 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2888899, "min": 1.3962282666666668, "max": 2.812616433333333, "count": 37 }, "Pyramids.Policy.Beta.mean": { "value": 0.006352864357857144, "min": 0.006352864357857144, "max": 0.009946171977142856, "count": 37 }, "Pyramids.Policy.Beta.sum": { "value": 0.08894010101000001, "min": 0.06962320384, "max": 0.13369784513, "count": 37 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008566516451537609, "min": 0.008566516451537609, "max": 0.4927542507648468, "count": 37 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11993123590946198, "min": 0.11993123590946198, "max": 3.44927978515625, "count": 37 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 305.16161616161617, "min": 287.6698113207547, "max": 999.0, "count": 37 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30211.0, "min": 15984.0, "max": 33309.0, "count": 37 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5878619851171971, "min": -1.0000000521540642, "max": 1.6934528171594412, "count": 37 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.7861985117197, "min": -25.830201491713524, "max": 179.50599861890078, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5878619851171971, "min": -1.0000000521540642, "max": 1.6934528171594412, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.7861985117197, "min": -25.830201491713524, "max": 179.50599861890078, "count": 37 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02777139512472786, "min": 0.027392642043269008, "max": 10.290611356496811, "count": 37 }, "Pyramids.Policy.RndReward.sum": { "value": 2.777139512472786, "min": 2.668499246588908, "max": 164.64978170394897, "count": 37 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706875710", "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 1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706878104" }, "total": 2393.907917657, "count": 1, "self": 0.41226748900044186, "children": { "run_training.setup": { "total": 0.04601177299991832, "count": 1, "self": 0.04601177299991832 }, "TrainerController.start_learning": { "total": 2393.4496383949995, "count": 1, "self": 1.38982433801948, "children": { "TrainerController._reset_env": { "total": 2.8399101289996906, "count": 1, "self": 2.8399101289996906 }, "TrainerController.advance": { "total": 2389.088251951979, "count": 71213, "self": 1.5297376669891491, "children": { "env_step": { "total": 1703.653578906008, "count": 71213, "self": 1560.409846672957, "children": { "SubprocessEnvManager._take_step": { "total": 142.36788957802128, "count": 71213, "self": 5.238596605027851, "children": { "TorchPolicy.evaluate": { "total": 137.12929297299343, "count": 69479, "self": 137.12929297299343 } } }, "workers": { "total": 0.8758426550298282, "count": 71212, "self": 0.0, "children": { "worker_root": { "total": 2387.9807726009694, "count": 71212, "is_parallel": true, "self": 953.7730105051587, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033214820000466716, "count": 1, "is_parallel": true, "self": 0.0008232330005739641, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024982489994727075, "count": 8, "is_parallel": true, "self": 0.0024982489994727075 } } }, "UnityEnvironment.step": { "total": 0.05002011099986703, "count": 1, "is_parallel": true, "self": 0.0005981559993415431, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005536230000871001, "count": 1, "is_parallel": true, "self": 0.0005536230000871001 }, "communicator.exchange": { "total": 0.047134647000348195, "count": 1, "is_parallel": true, "self": 0.047134647000348195 }, "steps_from_proto": { "total": 0.0017336850000901904, "count": 1, "is_parallel": true, "self": 0.00035011099907933385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013835740010108566, "count": 8, "is_parallel": true, "self": 0.0013835740010108566 } } } } } } }, "UnityEnvironment.step": { "total": 1434.2077620958107, "count": 71211, "is_parallel": true, "self": 38.5775411105833, "children": { "UnityEnvironment._generate_step_input": { "total": 28.361748394099777, "count": 71211, "is_parallel": true, "self": 28.361748394099777 }, "communicator.exchange": { "total": 1255.6464629360516, "count": 71211, "is_parallel": true, "self": 1255.6464629360516 }, "steps_from_proto": { "total": 111.622009655076, "count": 71211, "is_parallel": true, "self": 22.38032163379603, "children": { "_process_rank_one_or_two_observation": { "total": 89.24168802127997, "count": 569688, "is_parallel": true, "self": 89.24168802127997 } } } } } } } } } } }, "trainer_advance": { "total": 683.9049353789819, "count": 71212, "self": 2.7782892539667046, "children": { "process_trajectory": { "total": 141.3053483560143, "count": 71212, "self": 141.05603431601367, "children": { "RLTrainer._checkpoint": { "total": 0.24931404000062685, "count": 2, "self": 0.24931404000062685 } } }, "_update_policy": { "total": 539.8212977690009, "count": 508, "self": 316.59589603303857, "children": { "TorchPPOOptimizer.update": { "total": 223.22540173596235, "count": 25290, "self": 223.22540173596235 } } } } } } }, "trainer_threads": { "total": 1.6990006770356558e-06, "count": 1, "self": 1.6990006770356558e-06 }, "TrainerController._save_models": { "total": 0.13165027700051724, "count": 1, "self": 0.0020495340004345053, "children": { "RLTrainer._checkpoint": { "total": 0.12960074300008273, "count": 1, "self": 0.12960074300008273 } } } } } } }