{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42765557765960693, "min": 0.42765557765960693, "max": 1.444102168083191, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12870.72265625, "min": 12870.72265625, "max": 43808.28515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29898.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29898.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4740413427352905, "min": -0.09874321520328522, "max": 0.4740413427352905, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.8873291015625, "min": -23.895858764648438, "max": 129.8873291015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03468049690127373, "min": -0.01794944517314434, "max": 0.389791876077652, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.502455711364746, "min": -4.415563583374023, "max": 92.38067626953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06914377205109869, "min": 0.06457618965941948, "max": 0.07314545342860987, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9680128087153815, "min": 0.512018174000269, "max": 1.0247384742496983, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014910683606839963, "min": 0.0007184465922459686, "max": 0.015259525284214884, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20874957049575948, "min": 0.008621359106951623, "max": 0.22723277202692094, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.553368910814282e-06, "min": 7.553368910814282e-06, "max": 0.0002952352301596857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010574716475139994, "min": 0.00010574716475139994, "max": 0.0035086301304566993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251775714285714, "min": 0.10251775714285714, "max": 0.19841174285714283, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352486, "min": 1.3888821999999998, "max": 2.5695433000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002615239385714284, "min": 0.0002615239385714284, "max": 0.00984133311142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036613351399999976, "min": 0.0036613351399999976, "max": 0.11697737567, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014955240301787853, "min": 0.014570656232535839, "max": 0.5851942300796509, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2093733698129654, "min": 0.2039891928434372, "max": 4.096359729766846, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.60714285714283, "min": 373.3766233766234, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32139.0, "min": 16697.0, "max": 32660.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4744904537108683, "min": -0.9999500517733395, "max": 1.5850891702481218, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.85719811171293, "min": -31.998401656746864, "max": 123.85719811171293, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4744904537108683, "min": -0.9999500517733395, "max": 1.5850891702481218, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.85719811171293, "min": -31.998401656746864, "max": 123.85719811171293, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05839386045610289, "min": 0.05798116527395043, "max": 12.005578686209287, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.905084278312643, "min": 4.354132979293354, "max": 204.09483766555786, "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": "1716768730", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716770929" }, "total": 2199.116553324, "count": 1, "self": 0.49149433599995973, "children": { "run_training.setup": { "total": 0.05905033400000548, "count": 1, "self": 0.05905033400000548 }, "TrainerController.start_learning": { "total": 2198.566008654, "count": 1, "self": 1.3728440019467598, "children": { "TrainerController._reset_env": { "total": 3.583390558000019, "count": 1, "self": 3.583390558000019 }, "TrainerController.advance": { "total": 2193.5278139230536, "count": 63712, "self": 1.4751476040505622, "children": { "env_step": { "total": 1557.6710027870138, "count": 63712, "self": 1421.2972544070678, "children": { "SubprocessEnvManager._take_step": { "total": 135.52909868896427, "count": 63712, "self": 4.8602303339473, "children": { "TorchPolicy.evaluate": { "total": 130.66886835501697, "count": 62565, "self": 130.66886835501697 } } }, "workers": { "total": 0.8446496909817256, "count": 63712, "self": 0.0, "children": { "worker_root": { "total": 2193.1606817069996, "count": 63712, "is_parallel": true, "self": 896.3308822899546, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005354943999975603, "count": 1, "is_parallel": true, "self": 0.0037183160000040516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016366279999715516, "count": 8, "is_parallel": true, "self": 0.0016366279999715516 } } }, "UnityEnvironment.step": { "total": 0.05331802399996377, "count": 1, "is_parallel": true, "self": 0.0006684659999223186, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005170709999902101, "count": 1, "is_parallel": true, "self": 0.0005170709999902101 }, "communicator.exchange": { "total": 0.05034187100000054, "count": 1, "is_parallel": true, "self": 0.05034187100000054 }, "steps_from_proto": { "total": 0.0017906160000507043, "count": 1, "is_parallel": true, "self": 0.00037910000003194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014115160000187643, "count": 8, "is_parallel": true, "self": 0.0014115160000187643 } } } } } } }, "UnityEnvironment.step": { "total": 1296.829799417045, "count": 63711, "is_parallel": true, "self": 34.23944966314116, "children": { "UnityEnvironment._generate_step_input": { "total": 25.054391963900343, "count": 63711, "is_parallel": true, "self": 25.054391963900343 }, "communicator.exchange": { "total": 1135.802539698001, "count": 63711, "is_parallel": true, "self": 1135.802539698001 }, "steps_from_proto": { "total": 101.73341809200258, "count": 63711, "is_parallel": true, "self": 20.781884699940463, "children": { "_process_rank_one_or_two_observation": { "total": 80.95153339206212, "count": 509688, "is_parallel": true, "self": 80.95153339206212 } } } } } } } } } } }, "trainer_advance": { "total": 634.3816635319895, "count": 63712, "self": 2.5688455659959573, "children": { "process_trajectory": { "total": 133.11561347099212, "count": 63712, "self": 132.8561739279918, "children": { "RLTrainer._checkpoint": { "total": 0.259439543000326, "count": 2, "self": 0.259439543000326 } } }, "_update_policy": { "total": 498.6972044950014, "count": 451, "self": 294.2666973749966, "children": { "TorchPPOOptimizer.update": { "total": 204.4305071200048, "count": 22785, "self": 204.4305071200048 } } } } } } }, "trainer_threads": { "total": 1.2280002010811586e-06, "count": 1, "self": 1.2280002010811586e-06 }, "TrainerController._save_models": { "total": 0.08195894299979045, "count": 1, "self": 0.0014768779997211823, "children": { "RLTrainer._checkpoint": { "total": 0.08048206500006927, "count": 1, "self": 0.08048206500006927 } } } } } } }