{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2799193561077118, "min": 0.2799193561077118, "max": 1.397753119468689, "count": 55 }, "Pyramids.Policy.Entropy.sum": { "value": 8464.76171875, "min": 8464.76171875, "max": 42402.23828125, "count": 55 }, "Pyramids.Step.mean": { "value": 1649957.0, "min": 29952.0, "max": 1649957.0, "count": 55 }, "Pyramids.Step.sum": { "value": 1649957.0, "min": 29952.0, "max": 1649957.0, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7290536165237427, "min": -0.13940392434597015, "max": 0.7290536165237427, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 215.79986572265625, "min": -33.45694351196289, "max": 215.79986572265625, "count": 55 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.022374683991074562, "min": -0.022374683991074562, "max": 0.4695191979408264, "count": 55 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.62290620803833, "min": -6.62290620803833, "max": 112.68460845947266, "count": 55 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07144147636529798, "min": 0.06546259320089777, "max": 0.07600827309611133, "count": 55 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0716221454794697, "min": 0.5145730434636915, "max": 1.0716221454794697, "count": 55 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017299840395571663, "min": 0.0004578975269907725, "max": 0.017299840395571663, "count": 55 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25949760593357496, "min": 0.005952667850880043, "max": 0.25949760593357496, "count": 55 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013651903449367336, "min": 0.00013651903449367336, "max": 0.00029838354339596195, "count": 55 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020477855174051004, "min": 0.0019539499486836, "max": 0.003885643404785566, "count": 55 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14550632666666669, "min": 0.14550632666666669, "max": 0.19946118095238097, "count": 55 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1825949000000002, "min": 1.3897045333333333, "max": 2.695214433333333, "count": 55 }, "Pyramids.Policy.Beta.mean": { "value": 0.004556082034, "min": 0.004556082034, "max": 0.009946171977142856, "count": 55 }, "Pyramids.Policy.Beta.sum": { "value": 0.06834123051, "min": 0.06520650836, "max": 0.12953192189, "count": 55 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00995482224971056, "min": 0.009137672372162342, "max": 0.5962471961975098, "count": 55 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14932233095169067, "min": 0.12953078746795654, "max": 4.173730373382568, "count": 55 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 247.49606299212599, "min": 247.49606299212599, "max": 999.0, "count": 55 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31432.0, "min": 15984.0, "max": 33120.0, "count": 55 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7363888774481084, "min": -1.0000000521540642, "max": 1.7363888774481084, "count": 55 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 218.78499855846167, "min": -32.000001668930054, "max": 218.78499855846167, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7363888774481084, "min": -1.0000000521540642, "max": 1.7363888774481084, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 218.78499855846167, "min": -32.000001668930054, "max": 218.78499855846167, "count": 55 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02549890515353856, "min": 0.02549890515353856, "max": 11.26811558008194, "count": 55 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2128620493458584, "min": 2.761040462908568, "max": 180.28984928131104, "count": 55 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744414252", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsCPU --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744419732" }, "total": 5479.304351129, "count": 1, "self": 0.48942468200039, "children": { "run_training.setup": { "total": 0.02887916999998197, "count": 1, "self": 0.02887916999998197 }, "TrainerController.start_learning": { "total": 5478.786047277, "count": 1, "self": 4.171828854970045, "children": { "TrainerController._reset_env": { "total": 2.5432331959998464, "count": 1, "self": 2.5432331959998464 }, "TrainerController.advance": { "total": 5471.93044134803, "count": 107111, "self": 4.068886871048562, "children": { "env_step": { "total": 3654.8967864600654, "count": 107111, "self": 3379.2572125650377, "children": { "SubprocessEnvManager._take_step": { "total": 273.3068779119626, "count": 107111, "self": 11.290482349001877, "children": { "TorchPolicy.evaluate": { "total": 262.0163955629607, "count": 104404, "self": 262.0163955629607 } } }, "workers": { "total": 2.3326959830653777, "count": 107111, "self": 0.0, "children": { "worker_root": { "total": 5466.5211039610895, "count": 107111, "is_parallel": true, "self": 2374.5984374530312, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003052331000162667, "count": 1, "is_parallel": true, "self": 0.0010787760002131108, "children": { "_process_rank_one_or_two_observation": { "total": 0.001973554999949556, "count": 8, "is_parallel": true, "self": 0.001973554999949556 } } }, "UnityEnvironment.step": { "total": 0.059039665999989666, "count": 1, "is_parallel": true, "self": 0.000639636999949289, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005376090000481781, "count": 1, "is_parallel": true, "self": 0.0005376090000481781 }, "communicator.exchange": { "total": 0.055864005000103134, "count": 1, "is_parallel": true, "self": 0.055864005000103134 }, "steps_from_proto": { "total": 0.0019984149998890643, "count": 1, "is_parallel": true, "self": 0.00039714799981993565, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016012670000691287, "count": 8, "is_parallel": true, "self": 0.0016012670000691287 } } } } } } }, "UnityEnvironment.step": { "total": 3091.9226665080582, "count": 107110, "is_parallel": true, "self": 74.2024875929892, "children": { "UnityEnvironment._generate_step_input": { "total": 51.45809265497769, "count": 107110, "is_parallel": true, "self": 51.45809265497769 }, "communicator.exchange": { "total": 2751.4111133900706, "count": 107110, "is_parallel": true, "self": 2751.4111133900706 }, "steps_from_proto": { "total": 214.85097287002054, "count": 107110, "is_parallel": true, "self": 45.91508233276227, "children": { "_process_rank_one_or_two_observation": { "total": 168.93589053725827, "count": 856880, "is_parallel": true, "self": 168.93589053725827 } } } } } } } } } } }, "trainer_advance": { "total": 1812.964768016916, "count": 107110, "self": 7.87644274299646, "children": { "process_trajectory": { "total": 270.22854500190965, "count": 107110, "self": 269.8536964699099, "children": { "RLTrainer._checkpoint": { "total": 0.37484853199975987, "count": 3, "self": 0.37484853199975987 } } }, "_update_policy": { "total": 1534.8597802720099, "count": 764, "self": 605.1324144159878, "children": { "TorchPPOOptimizer.update": { "total": 929.7273658560221, "count": 38088, "self": 929.7273658560221 } } } } } } }, "trainer_threads": { "total": 1.4849993021925911e-06, "count": 1, "self": 1.4849993021925911e-06 }, "TrainerController._save_models": { "total": 0.14054239300003246, "count": 1, "self": 0.0028463919998102938, "children": { "RLTrainer._checkpoint": { "total": 0.13769600100022217, "count": 1, "self": 0.13769600100022217 } } } } } } }