| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.17291924357414246, |
| "min": 0.15377093851566315, |
| "max": 1.4117788076400757, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5206.9443359375, |
| "min": 4659.87451171875, |
| "max": 42827.72265625, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999976.0, |
| "min": 29887.0, |
| "max": 2999976.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999976.0, |
| "min": 29887.0, |
| "max": 2999976.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8608826398849487, |
| "min": -0.10265273600816727, |
| "max": 0.8739694356918335, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 267.7344970703125, |
| "min": -24.739309310913086, |
| "max": 267.7344970703125, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.007689562626183033, |
| "min": -0.03204171732068062, |
| "max": 0.34547337889671326, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -2.391453981399536, |
| "min": -9.452306747436523, |
| "max": 81.87718963623047, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06951443805952467, |
| "min": 0.0630331672208758, |
| "max": 0.07449299893299567, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9732021328333454, |
| "min": 0.5524288011025276, |
| "max": 1.0564465693228962, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01517638965119009, |
| "min": 0.0012198266929550256, |
| "max": 0.015419875266421251, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21246945511666127, |
| "min": 0.012433926611563818, |
| "max": 0.22976893667838144, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4484923743452395e-06, |
| "min": 1.4484923743452395e-06, |
| "max": 0.0002984059630313458, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.027889324083335e-05, |
| "min": 2.027889324083335e-05, |
| "max": 0.0039691244769585335, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10048279761904765, |
| "min": 0.10048279761904765, |
| "max": 0.1994686541666667, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.406759166666667, |
| "min": 1.406759166666667, |
| "max": 2.723041466666666, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.8231482142857186e-05, |
| "min": 5.8231482142857186e-05, |
| "max": 0.00994691855125, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008152407500000006, |
| "min": 0.0008152407500000006, |
| "max": 0.13231184252, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.005447447765618563, |
| "min": 0.005309185944497585, |
| "max": 0.4513447880744934, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.07626426964998245, |
| "min": 0.07432860136032104, |
| "max": 3.6107583045959473, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 208.05333333333334, |
| "min": 204.4160583941606, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31208.0, |
| "min": 15919.0, |
| "max": 33281.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7786066532631715, |
| "min": -0.9999500517733395, |
| "max": 1.7955839335918427, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 266.7909979894757, |
| "min": -31.998401656746864, |
| "max": 266.7909979894757, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7786066532631715, |
| "min": -0.9999500517733395, |
| "max": 1.7955839335918427, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 266.7909979894757, |
| "min": -31.998401656746864, |
| "max": 266.7909979894757, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.011840315460212879, |
| "min": 0.011824341663614448, |
| "max": 9.361570369452238, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.7760473190319317, |
| "min": 1.5844617829243361, |
| "max": 149.7851259112358, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1740376031", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "command_line_arguments": "/home/alien/.local/share/mamba/envs/deep-rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1740379184" |
| }, |
| "total": 3152.4720249649836, |
| "count": 1, |
| "self": 0.21816878096433356, |
| "children": { |
| "run_training.setup": { |
| "total": 0.01668302499456331, |
| "count": 1, |
| "self": 0.01668302499456331 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3152.2371731590247, |
| "count": 1, |
| "self": 2.5445676614763215, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.55027294595493, |
| "count": 1, |
| "self": 1.55027294595493 |
| }, |
| "TrainerController.advance": { |
| "total": 3148.0890001385706, |
| "count": 195212, |
| "self": 2.5107865219470114, |
| "children": { |
| "env_step": { |
| "total": 2009.3240775034064, |
| "count": 195212, |
| "self": 1729.7895267679123, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 277.89236204046756, |
| "count": 195212, |
| "self": 7.317112011776771, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 270.5752500286908, |
| "count": 187559, |
| "self": 270.5752500286908 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.6421886950265616, |
| "count": 195212, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3148.800737663987, |
| "count": 195212, |
| "is_parallel": true, |
| "self": 1594.055274826591, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0009371869964525104, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00026788696413859725, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0006693000323139131, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0006693000323139131 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.019988799991551787, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00022407196229323745, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00016757601406425238, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00016757601406425238 |
| }, |
| "communicator.exchange": { |
| "total": 0.019009742012713104, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.019009742012713104 |
| }, |
| "steps_from_proto": { |
| "total": 0.0005874100024811924, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00013781210873275995, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0004495978937484324, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0004495978937484324 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1554.7454628373962, |
| "count": 195211, |
| "is_parallel": true, |
| "self": 47.04075167508563, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 24.893535839451943, |
| "count": 195211, |
| "is_parallel": true, |
| "self": 24.893535839451943 |
| }, |
| "communicator.exchange": { |
| "total": 1352.8311300514033, |
| "count": 195211, |
| "is_parallel": true, |
| "self": 1352.8311300514033 |
| }, |
| "steps_from_proto": { |
| "total": 129.9800452714553, |
| "count": 195211, |
| "is_parallel": true, |
| "self": 26.629174274159595, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 103.35087099729571, |
| "count": 1561688, |
| "is_parallel": true, |
| "self": 103.35087099729571 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1136.254136113217, |
| "count": 195212, |
| "self": 4.513091377855744, |
| "children": { |
| "process_trajectory": { |
| "total": 221.54046510130865, |
| "count": 195212, |
| "self": 221.22121832327684, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3192467780318111, |
| "count": 6, |
| "self": 0.3192467780318111 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 910.2005796340527, |
| "count": 1397, |
| "self": 478.96880203904584, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 431.23177759500686, |
| "count": 68391, |
| "self": 431.23177759500686 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 6.799818947911263e-07, |
| "count": 1, |
| "self": 6.799818947911263e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.05333173304097727, |
| "count": 1, |
| "self": 0.000749443017411977, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.05258229002356529, |
| "count": 1, |
| "self": 0.05258229002356529 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
