{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6582197546958923, "min": 0.6582197546958923, "max": 1.4857103824615479, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19778.1875, "min": 19778.1875, "max": 45070.51171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.34232568740844727, "min": -0.21555005013942719, "max": 0.4189187288284302, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 89.6893310546875, "min": -51.08536148071289, "max": 112.27021789550781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00566603010520339, "min": -0.002149995882064104, "max": 0.2953774631023407, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4844999313354492, "min": -0.5697489380836487, "max": 70.00445556640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06853258555998938, "min": 0.06531036150582398, "max": 0.07275970583852011, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9594561978398513, "min": 0.49417190839858977, "max": 1.0340315212048226, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011694101730556997, "min": 0.0001747867651937809, "max": 0.013626769085882895, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16371742422779795, "min": 0.0022722279475191516, "max": 0.19077476720236053, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.350590406978569e-06, "min": 7.350590406978569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010290826569769996, "min": 0.00010290826569769996, "max": 0.0035073536308821993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024501642857143, "min": 0.1024501642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343023000000001, "min": 1.3886848, "max": 2.5691178000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002547714121428571, "min": 0.0002547714121428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035667997699999994, "min": 0.0035667997699999994, "max": 0.11693486821999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009588450193405151, "min": 0.009588450193405151, "max": 0.3562386631965637, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13423830270767212, "min": 0.13423830270767212, "max": 2.493670701980591, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 482.42622950819674, "min": 454.85074626865674, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29428.0, "min": 15984.0, "max": 32992.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2551835816903192, "min": -1.0000000521540642, "max": 1.4555581845899126, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 76.56619848310947, "min": -31.99680168926716, "max": 97.52239836752415, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2551835816903192, "min": -1.0000000521540642, "max": 1.4555581845899126, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 76.56619848310947, "min": -31.99680168926716, "max": 97.52239836752415, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04768418025303647, "min": 0.0456898459311533, "max": 7.947462385054678, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.908734995435225, "min": 2.908734995435225, "max": 127.15939816087484, "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": "1699466360", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699468533" }, "total": 2173.6519661160005, "count": 1, "self": 0.5765998490001039, "children": { "run_training.setup": { "total": 0.040772619000108534, "count": 1, "self": 0.040772619000108534 }, "TrainerController.start_learning": { "total": 2173.0345936480003, "count": 1, "self": 1.3792977400594282, "children": { "TrainerController._reset_env": { "total": 3.4425388829999974, "count": 1, "self": 3.4425388829999974 }, "TrainerController.advance": { "total": 2168.1375249099415, "count": 63383, "self": 1.4181992019557583, "children": { "env_step": { "total": 1535.2488306299983, "count": 63383, "self": 1400.759572539032, "children": { "SubprocessEnvManager._take_step": { "total": 133.6288033199903, "count": 63383, "self": 4.651064258031511, "children": { "TorchPolicy.evaluate": { "total": 128.9777390619588, "count": 62554, "self": 128.9777390619588 } } }, "workers": { "total": 0.8604547709760482, "count": 63383, "self": 0.0, "children": { "worker_root": { "total": 2168.2852865001164, "count": 63383, "is_parallel": true, "self": 888.7236655020965, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023036030002003827, "count": 1, "is_parallel": true, "self": 0.0010890640014622477, "children": { "_process_rank_one_or_two_observation": { "total": 0.001214538998738135, "count": 8, "is_parallel": true, "self": 0.001214538998738135 } } }, "UnityEnvironment.step": { "total": 0.05155775299999732, "count": 1, "is_parallel": true, "self": 0.0007745489997432742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005119410002407676, "count": 1, "is_parallel": true, "self": 0.0005119410002407676 }, "communicator.exchange": { "total": 0.04836888199997702, "count": 1, "is_parallel": true, "self": 0.04836888199997702 }, "steps_from_proto": { "total": 0.0019023810000362573, "count": 1, "is_parallel": true, "self": 0.0003906789993379789, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015117020006982784, "count": 8, "is_parallel": true, "self": 0.0015117020006982784 } } } } } } }, "UnityEnvironment.step": { "total": 1279.5616209980199, "count": 63382, "is_parallel": true, "self": 35.48726316592138, "children": { "UnityEnvironment._generate_step_input": { "total": 26.061340590052623, "count": 63382, "is_parallel": true, "self": 26.061340590052623 }, "communicator.exchange": { "total": 1112.8768973930382, "count": 63382, "is_parallel": true, "self": 1112.8768973930382 }, "steps_from_proto": { "total": 105.13611984900763, "count": 63382, "is_parallel": true, "self": 21.255029476914387, "children": { "_process_rank_one_or_two_observation": { "total": 83.88109037209324, "count": 507056, "is_parallel": true, "self": 83.88109037209324 } } } } } } } } } } }, "trainer_advance": { "total": 631.4704950779874, "count": 63383, "self": 2.5765435710713973, "children": { "process_trajectory": { "total": 125.80892255992376, "count": 63383, "self": 125.58306548792325, "children": { "RLTrainer._checkpoint": { "total": 0.2258570720005082, "count": 2, "self": 0.2258570720005082 } } }, "_update_policy": { "total": 503.0850289469922, "count": 445, "self": 297.5838996999855, "children": { "TorchPPOOptimizer.update": { "total": 205.5011292470067, "count": 22857, "self": 205.5011292470067 } } } } } } }, "trainer_threads": { "total": 1.065999640559312e-06, "count": 1, "self": 1.065999640559312e-06 }, "TrainerController._save_models": { "total": 0.07523104899973987, "count": 1, "self": 0.0014802519999648212, "children": { "RLTrainer._checkpoint": { "total": 0.07375079699977505, "count": 1, "self": 0.07375079699977505 } } } } } } }