{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14705009758472443, "min": 0.14705009758472443, "max": 1.4738560914993286, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4519.73193359375, "min": 4519.73193359375, "max": 44710.8984375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999979.0, "min": 29952.0, "max": 2999979.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999979.0, "min": 29952.0, "max": 2999979.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7882036566734314, "min": -0.159807950258255, "max": 0.8982242941856384, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 234.0964813232422, "min": -37.87448501586914, "max": 278.44952392578125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00041883415542542934, "min": -0.008426296524703503, "max": 0.22714480757713318, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.12439374625682831, "min": -2.2076897621154785, "max": 54.74189758300781, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0711198105668458, "min": 0.06454486250281447, "max": 0.07466311073212548, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9956773479358412, "min": 0.4895428951494141, "max": 1.0921828447608277, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012428539642006459, "min": 0.0001801656448933367, "max": 0.015175789196204973, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17399955498809042, "min": 0.002342153383613377, "max": 0.21705833335484687, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.460735227407142e-06, "min": 1.460735227407142e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.045029318369999e-05, "min": 2.045029318369999e-05, "max": 0.004011016762994433, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048687857142856, "min": 0.10048687857142856, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068162999999998, "min": 1.3962282666666668, "max": 2.7975871000000003, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.863916928571428e-05, "min": 5.863916928571428e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008209483699999999, "min": 0.0008209483699999999, "max": 0.13370685611, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005229505710303783, "min": 0.005229505710303783, "max": 0.3420969545841217, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07321307808160782, "min": 0.07321307808160782, "max": 2.3946785926818848, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 222.42857142857142, "min": 205.42, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29583.0, "min": 15984.0, "max": 33312.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7609746076945048, "min": -1.0000000521540642, "max": 1.794579989016056, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 235.97059743106365, "min": -31.991201624274254, "max": 269.1869983524084, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7609746076945048, "min": -1.0000000521540642, "max": 1.794579989016056, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 235.97059743106365, "min": -31.991201624274254, "max": 269.1869983524084, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012439756828717324, "min": 0.0121526422872, "max": 6.856110998429358, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6669274150481215, "min": 1.6669274150481215, "max": 109.69777597486973, "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": "1676971723", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676979138" }, "total": 7414.809118518, "count": 1, "self": 0.5182456399988951, "children": { "run_training.setup": { "total": 0.11610462400005872, "count": 1, "self": 0.11610462400005872 }, "TrainerController.start_learning": { "total": 7414.174768254001, "count": 1, "self": 4.451238328942964, "children": { "TrainerController._reset_env": { "total": 10.447927342000071, "count": 1, "self": 10.447927342000071 }, "TrainerController.advance": { "total": 7399.190986399058, "count": 195105, "self": 4.642443494440158, "children": { "env_step": { "total": 5187.166534398786, "count": 195105, "self": 4830.6579297710905, "children": { "SubprocessEnvManager._take_step": { "total": 353.77259816477056, "count": 195105, "self": 14.093807816535332, "children": { "TorchPolicy.evaluate": { "total": 339.6787903482352, "count": 187575, "self": 113.83060502037142, "children": { "TorchPolicy.sample_actions": { "total": 225.8481853278638, "count": 187575, "self": 225.8481853278638 } } } } }, "workers": { "total": 2.7360064629250473, "count": 195105, "self": 0.0, "children": { "worker_root": { "total": 7397.649235723051, "count": 195105, "is_parallel": true, "self": 2930.1017951701033, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005948508999949809, "count": 1, "is_parallel": true, "self": 0.003302439999629314, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026460690003204945, "count": 8, "is_parallel": true, "self": 0.0026460690003204945 } } }, "UnityEnvironment.step": { "total": 0.053843427999936466, "count": 1, "is_parallel": true, "self": 0.0005534809999971912, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004549599999563725, "count": 1, "is_parallel": true, "self": 0.0004549599999563725 }, "communicator.exchange": { "total": 0.051214996999988216, "count": 1, "is_parallel": true, "self": 0.051214996999988216 }, "steps_from_proto": { "total": 0.0016199899999946865, "count": 1, "is_parallel": true, "self": 0.00039988299988635845, "children": { "_process_rank_one_or_two_observation": { "total": 0.001220107000108328, "count": 8, "is_parallel": true, "self": 0.001220107000108328 } } } } } } }, "UnityEnvironment.step": { "total": 4467.547440552948, "count": 195104, "is_parallel": true, "self": 95.89912010720855, "children": { "UnityEnvironment._generate_step_input": { "total": 67.77056174275174, "count": 195104, "is_parallel": true, "self": 67.77056174275174 }, "communicator.exchange": { "total": 4020.5038098050495, "count": 195104, "is_parallel": true, "self": 4020.5038098050495 }, "steps_from_proto": { "total": 283.37394889793745, "count": 195104, "is_parallel": true, "self": 68.15375735952023, "children": { "_process_rank_one_or_two_observation": { "total": 215.22019153841723, "count": 1560832, "is_parallel": true, "self": 215.22019153841723 } } } } } } } } } } }, "trainer_advance": { "total": 2207.3820085058314, "count": 195105, "self": 9.043388606036388, "children": { "process_trajectory": { "total": 491.75917273879463, "count": 195105, "self": 491.20175605479426, "children": { "RLTrainer._checkpoint": { "total": 0.5574166840003727, "count": 6, "self": 0.5574166840003727 } } }, "_update_policy": { "total": 1706.5794471610006, "count": 1396, "self": 664.3680366629951, "children": { "TorchPPOOptimizer.update": { "total": 1042.2114104980055, "count": 68349, "self": 1042.2114104980055 } } } } } } }, "trainer_threads": { "total": 8.289998731925152e-07, "count": 1, "self": 8.289998731925152e-07 }, "TrainerController._save_models": { "total": 0.08461535500009632, "count": 1, "self": 0.001406336000400188, "children": { "RLTrainer._checkpoint": { "total": 0.08320901899969613, "count": 1, "self": 0.08320901899969613 } } } } } } }