{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4008009135723114, "min": 0.39429911971092224, "max": 1.4864692687988281, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12203.5859375, "min": 11633.4013671875, "max": 45093.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43186134099960327, "min": -0.15425889194011688, "max": 0.46505916118621826, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.17070007324219, "min": -36.559356689453125, "max": 124.51618957519531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012000525370240211, "min": -0.07429196685552597, "max": 0.38535016775131226, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.2281413078308105, "min": -19.167327880859375, "max": 91.32798767089844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0673022839990962, "min": 0.06160194265929438, "max": 0.07364860322160616, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.009534259986443, "min": 0.49885727858204987, "max": 1.0790244572563095, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015669423356303013, "min": 0.00025509256945460695, "max": 0.015669423356303013, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2350413503445452, "min": 0.0033162034029098906, "max": 0.2350413503445452, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.615677461473333e-06, "min": 7.615677461473333e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001142351619221, "min": 0.0001142351619221, "max": 0.0032527919157361003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253852666666669, "min": 0.10253852666666669, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5380779000000002, "min": 1.3886848, "max": 2.4432250000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026359881400000014, "min": 0.00026359881400000014, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003953982210000002, "min": 0.003953982210000002, "max": 0.10844796361, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009066877886652946, "min": 0.009066877886652946, "max": 0.3583345413208008, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13600316643714905, "min": 0.12746194005012512, "max": 2.5083417892456055, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 410.4583333333333, "min": 388.9861111111111, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29553.0, "min": 15984.0, "max": 32606.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.423849287608715, "min": -1.0000000521540642, "max": 1.4998527529338996, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.94099799543619, "min": -31.998401656746864, "max": 111.16399851441383, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.423849287608715, "min": -1.0000000521540642, "max": 1.4998527529338996, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.94099799543619, "min": -31.998401656746864, "max": 111.16399851441383, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0395681949787652, "min": 0.037773463895577244, "max": 7.587340063415468, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8884782334498595, "min": 2.794820085167885, "max": 121.39744101464748, "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": "1709084671", "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": "1709086840" }, "total": 2168.522633816, "count": 1, "self": 0.588928917999965, "children": { "run_training.setup": { "total": 0.04979802900004415, "count": 1, "self": 0.04979802900004415 }, "TrainerController.start_learning": { "total": 2167.883906869, "count": 1, "self": 1.307805577995623, "children": { "TrainerController._reset_env": { "total": 3.8173097899999675, "count": 1, "self": 3.8173097899999675 }, "TrainerController.advance": { "total": 2162.669970590005, "count": 63637, "self": 1.337615639924934, "children": { "env_step": { "total": 1553.196025244024, "count": 63637, "self": 1430.1778439550199, "children": { "SubprocessEnvManager._take_step": { "total": 122.26481718999776, "count": 63637, "self": 4.509609150047709, "children": { "TorchPolicy.evaluate": { "total": 117.75520803995005, "count": 62557, "self": 117.75520803995005 } } }, "workers": { "total": 0.7533640990063759, "count": 63637, "self": 0.0, "children": { "worker_root": { "total": 2163.339940679044, "count": 63637, "is_parallel": true, "self": 842.5975141120205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005324147000010271, "count": 1, "is_parallel": true, "self": 0.003926271000295856, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013978759997144152, "count": 8, "is_parallel": true, "self": 0.0013978759997144152 } } }, "UnityEnvironment.step": { "total": 0.05467806100000416, "count": 1, "is_parallel": true, "self": 0.0006217069999365776, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004636750001054679, "count": 1, "is_parallel": true, "self": 0.0004636750001054679 }, "communicator.exchange": { "total": 0.05209857899990311, "count": 1, "is_parallel": true, "self": 0.05209857899990311 }, "steps_from_proto": { "total": 0.0014941000000590066, "count": 1, "is_parallel": true, "self": 0.0003200080003580297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011740919997009769, "count": 8, "is_parallel": true, "self": 0.0011740919997009769 } } } } } } }, "UnityEnvironment.step": { "total": 1320.7424265670236, "count": 63636, "is_parallel": true, "self": 34.68668316697881, "children": { "UnityEnvironment._generate_step_input": { "total": 23.75025075902181, "count": 63636, "is_parallel": true, "self": 23.75025075902181 }, "communicator.exchange": { "total": 1165.6740645299803, "count": 63636, "is_parallel": true, "self": 1165.6740645299803 }, "steps_from_proto": { "total": 96.63142811104274, "count": 63636, "is_parallel": true, "self": 18.564439055146636, "children": { "_process_rank_one_or_two_observation": { "total": 78.0669890558961, "count": 509088, "is_parallel": true, "self": 78.0669890558961 } } } } } } } } } } }, "trainer_advance": { "total": 608.1363297060561, "count": 63637, "self": 2.383970583997211, "children": { "process_trajectory": { "total": 121.91104898006017, "count": 63637, "self": 121.71631420706024, "children": { "RLTrainer._checkpoint": { "total": 0.19473477299993647, "count": 2, "self": 0.19473477299993647 } } }, "_update_policy": { "total": 483.84131014199875, "count": 445, "self": 281.9110591780043, "children": { "TorchPPOOptimizer.update": { "total": 201.93025096399447, "count": 22872, "self": 201.93025096399447 } } } } } } }, "trainer_threads": { "total": 8.449997039861046e-07, "count": 1, "self": 8.449997039861046e-07 }, "TrainerController._save_models": { "total": 0.08882006599969827, "count": 1, "self": 0.0013936319996901148, "children": { "RLTrainer._checkpoint": { "total": 0.08742643400000816, "count": 1, "self": 0.08742643400000816 } } } } } } }