{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18231630325317383, "min": 0.16655932366847992, "max": 1.4087858200073242, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5469.4892578125, "min": 5007.439453125, "max": 42736.92578125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999893.0, "min": 29952.0, "max": 2999893.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999893.0, "min": 29952.0, "max": 2999893.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8156356811523438, "min": -0.10658009350299835, "max": 0.9129963517189026, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.42816162109375, "min": -25.685802459716797, "max": 280.2898864746094, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0014183419989421964, "min": -0.04452037811279297, "max": 0.47088423371315, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.41982921957969666, "min": -11.486257553100586, "max": 111.59956359863281, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07125119070683252, "min": 0.06320074805366208, "max": 0.07388558232055499, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9975166698956551, "min": 0.5168598278876577, "max": 1.0987159707874523, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014267679930309808, "min": 0.00011777798141151257, "max": 0.017450077489705847, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19974751902433732, "min": 0.001413335776938151, "max": 0.24430108485588184, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4286780952357172e-06, "min": 1.4286780952357172e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.000149333330004e-05, "min": 2.000149333330004e-05, "max": 0.0037592781469073327, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047619285714286, "min": 0.10047619285714286, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066667000000002, "min": 1.3962282666666668, "max": 2.737579033333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.757166642857155e-05, "min": 5.757166642857155e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008060033300000017, "min": 0.0008060033300000017, "max": 0.12532395740000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006158839445561171, "min": 0.006035138852894306, "max": 0.5842918753623962, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08622375130653381, "min": 0.08622375130653381, "max": 4.090043067932129, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 230.1984126984127, "min": 190.64102564102564, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29005.0, "min": 15984.0, "max": 32776.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.753920621519524, "min": -1.0000000521540642, "max": 1.8097483716664775, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 220.99399831146002, "min": -31.99640165269375, "max": 280.510997608304, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.753920621519524, "min": -1.0000000521540642, "max": 1.8097483716664775, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 220.99399831146002, "min": -31.99640165269375, "max": 280.510997608304, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014766185671991451, "min": 0.012547770574981828, "max": 12.09333622828126, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8605393946709228, "min": 1.8605393946709228, "max": 193.49337965250015, "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": "1733054010", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/zhangsz/anaconda3/envs/deep_rl_course/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1733058351" }, "total": 4341.057121403002, "count": 1, "self": 10.003593190001993, "children": { "run_training.setup": { "total": 0.013588231999165146, "count": 1, "self": 0.013588231999165146 }, "TrainerController.start_learning": { "total": 4331.039939981001, "count": 1, "self": 2.9615243840235053, "children": { "TrainerController._reset_env": { "total": 5.872060842997598, "count": 1, "self": 5.872060842997598 }, "TrainerController.advance": { "total": 4322.13732466998, "count": 194853, "self": 2.4629192777501885, "children": { "env_step": { "total": 2765.3507514890152, "count": 194853, "self": 2213.2033783642473, "children": { "SubprocessEnvManager._take_step": { "total": 550.2206959732757, "count": 194853, "self": 8.09100237117309, "children": { "TorchPolicy.evaluate": { "total": 542.1296936021026, "count": 187554, "self": 542.1296936021026 } } }, "workers": { "total": 1.9266771514921857, "count": 194853, "self": 0.0, "children": { "worker_root": { "total": 4325.04798421116, "count": 194853, "is_parallel": true, "self": 2287.896569750392, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014852139975118916, "count": 1, "is_parallel": true, "self": 0.000792052989709191, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006931610078027006, "count": 8, "is_parallel": true, "self": 0.0006931610078027006 } } }, "UnityEnvironment.step": { "total": 0.0232249859982403, "count": 1, "is_parallel": true, "self": 0.00018313400141778402, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001442969987692777, "count": 1, "is_parallel": true, "self": 0.0001442969987692777 }, "communicator.exchange": { "total": 0.022439027998188976, "count": 1, "is_parallel": true, "self": 0.022439027998188976 }, "steps_from_proto": { "total": 0.0004585269998642616, "count": 1, "is_parallel": true, "self": 0.00011709200771292672, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003414349921513349, "count": 8, "is_parallel": true, "self": 0.0003414349921513349 } } } } } } }, "UnityEnvironment.step": { "total": 2037.1514144607681, "count": 194852, "is_parallel": true, "self": 28.920518112521677, "children": { "UnityEnvironment._generate_step_input": { "total": 19.860413033664372, "count": 194852, "is_parallel": true, "self": 19.860413033664372 }, "communicator.exchange": { "total": 1908.1999124171816, "count": 194852, "is_parallel": true, "self": 1908.1999124171816 }, "steps_from_proto": { "total": 80.17057089740047, "count": 194852, "is_parallel": true, "self": 20.057851851001033, "children": { "_process_rank_one_or_two_observation": { "total": 60.112719046399434, "count": 1558816, "is_parallel": true, "self": 60.112719046399434 } } } } } } } } } } }, "trainer_advance": { "total": 1554.323653903215, "count": 194853, "self": 5.708780029217451, "children": { "process_trajectory": { "total": 287.43335927692897, "count": 194853, "self": 286.99231168692495, "children": { "RLTrainer._checkpoint": { "total": 0.4410475900040183, "count": 6, "self": 0.4410475900040183 } } }, "_update_policy": { "total": 1261.1815145970686, "count": 1393, "self": 604.4488395120279, "children": { "TorchPPOOptimizer.update": { "total": 656.7326750850407, "count": 68469, "self": 656.7326750850407 } } } } } } }, "trainer_threads": { "total": 5.699985194951296e-07, "count": 1, "self": 5.699985194951296e-07 }, "TrainerController._save_models": { "total": 0.06902951400115853, "count": 1, "self": 0.0006922620013938285, "children": { "RLTrainer._checkpoint": { "total": 0.0683372519997647, "count": 1, "self": 0.0683372519997647 } } } } } } }