{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30435580015182495, "min": 0.2899474501609802, "max": 1.423551321029663, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9150.15234375, "min": 8665.94921875, "max": 43184.8515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5753867030143738, "min": -0.10824465751647949, "max": 0.6366127729415894, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.95750427246094, "min": -26.08696174621582, "max": 175.7051239013672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019443243741989136, "min": -0.02532048337161541, "max": 0.47839128971099854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.405221939086914, "min": -6.861851215362549, "max": 113.37873840332031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06727541594112509, "min": 0.06412143563266866, "max": 0.07488208898853156, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9418558231757511, "min": 0.49326203957251236, "max": 1.0516347347972137, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013766548244284398, "min": 0.0013429418554619466, "max": 0.015423129470564009, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19273167541998157, "min": 0.014926287783274693, "max": 0.2159238125878961, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.273404718421427e-06, "min": 7.273404718421427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010182766605789998, "min": 0.00010182766605789998, "max": 0.0035090444303186004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242443571428571, "min": 0.10242443571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339420999999999, "min": 1.3886848, "max": 2.5696814, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025220112785714286, "min": 0.00025220112785714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00353081579, "min": 0.00353081579, "max": 0.11699117185999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011673234403133392, "min": 0.011673234403133392, "max": 0.45363110303878784, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1634252816438675, "min": 0.1634252816438675, "max": 3.17541766166687, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 343.95402298850576, "min": 296.37113402061857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29924.0, "min": 15984.0, "max": 32574.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6067720772048761, "min": -1.0000000521540642, "max": 1.6274956321424765, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.18239863961935, "min": -30.606001675128937, "max": 159.0201978981495, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6067720772048761, "min": -1.0000000521540642, "max": 1.6274956321424765, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.18239863961935, "min": -30.606001675128937, "max": 159.0201978981495, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04194443959500478, "min": 0.03835174736325696, "max": 8.673695949837565, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6072218051704112, "min": 3.6072218051704112, "max": 138.77913519740105, "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": "1757330476", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/home/test/Saranya/reinforcement_learning/rl/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1757331359" }, "total": 882.5172978179999, "count": 1, "self": 0.218555087999448, "children": { "run_training.setup": { "total": 0.014362036999955308, "count": 1, "self": 0.014362036999955308 }, "TrainerController.start_learning": { "total": 882.2843806930005, "count": 1, "self": 0.8982118690119023, "children": { "TrainerController._reset_env": { "total": 1.050187034999908, "count": 1, "self": 1.050187034999908 }, "TrainerController.advance": { "total": 880.3054112579894, "count": 64067, "self": 0.859885600933012, "children": { "env_step": { "total": 560.845441444123, "count": 64067, "self": 510.3397095652881, "children": { "SubprocessEnvManager._take_step": { "total": 49.97661440482989, "count": 64067, "self": 2.48758906180592, "children": { "TorchPolicy.evaluate": { "total": 47.48902534302397, "count": 62570, "self": 47.48902534302397 } } }, "workers": { "total": 0.5291174740050337, "count": 64067, "self": 0.0, "children": { "worker_root": { "total": 881.1485519160024, "count": 64067, "is_parallel": true, "self": 429.535817742938, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009040510003615054, "count": 1, "is_parallel": true, "self": 0.000251975997343834, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006520750030176714, "count": 8, "is_parallel": true, "self": 0.0006520750030176714 } } }, "UnityEnvironment.step": { "total": 0.023619386999598646, "count": 1, "is_parallel": true, "self": 0.00019218200122850249, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016745099947002018, "count": 1, "is_parallel": true, "self": 0.00016745099947002018 }, "communicator.exchange": { "total": 0.0227110959995116, "count": 1, "is_parallel": true, "self": 0.0227110959995116 }, "steps_from_proto": { "total": 0.0005486579993885243, "count": 1, "is_parallel": true, "self": 0.00012860900005762232, "children": { "_process_rank_one_or_two_observation": { "total": 0.000420048999330902, "count": 8, "is_parallel": true, "self": 0.000420048999330902 } } } } } } }, "UnityEnvironment.step": { "total": 451.6127341730644, "count": 64066, "is_parallel": true, "self": 12.580359135216895, "children": { "UnityEnvironment._generate_step_input": { "total": 8.353070208901045, "count": 64066, "is_parallel": true, "self": 8.353070208901045 }, "communicator.exchange": { "total": 396.7872556150742, "count": 64066, "is_parallel": true, "self": 396.7872556150742 }, "steps_from_proto": { "total": 33.89204921387227, "count": 64066, "is_parallel": true, "self": 7.362607668226701, "children": { "_process_rank_one_or_two_observation": { "total": 26.529441545645568, "count": 512528, "is_parallel": true, "self": 26.529441545645568 } } } } } } } } } } }, "trainer_advance": { "total": 318.6000842129333, "count": 64067, "self": 1.6477648118907382, "children": { "process_trajectory": { "total": 60.02991463705348, "count": 64067, "self": 59.94905758305322, "children": { "RLTrainer._checkpoint": { "total": 0.080857054000262, "count": 2, "self": 0.080857054000262 } } }, "_update_policy": { "total": 256.9224047639891, "count": 452, "self": 131.36834416703277, "children": { "TorchPPOOptimizer.update": { "total": 125.55406059695633, "count": 22788, "self": 125.55406059695633 } } } } } } }, "trainer_threads": { "total": 6.04999513598159e-07, "count": 1, "self": 6.04999513598159e-07 }, "TrainerController._save_models": { "total": 0.03056992599977093, "count": 1, "self": 0.0007708249995630467, "children": { "RLTrainer._checkpoint": { "total": 0.029799101000207884, "count": 1, "self": 0.029799101000207884 } } } } } } }