{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.24013368785381317, "min": 0.22398802638053894, "max": 1.4401417970657349, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 7188.64208984375, "min": 6726.80859375, "max": 43688.140625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999998.0, "min": 29904.0, "max": 2999998.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999998.0, "min": 29904.0, "max": 2999998.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.704486608505249, "min": -0.11792903393507004, "max": 0.740608811378479, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 201.48316955566406, "min": -28.420896530151367, "max": 214.77655029296875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00505731301382184, "min": -0.011330563575029373, "max": 0.3952215313911438, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4463915824890137, "min": -3.161227226257324, "max": 94.0627212524414, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06801170255634699, "min": 0.06485316155794635, "max": 0.07297866407038997, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9521638357888579, "min": 0.5775773482612634, "max": 1.0838847862614784, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01434359999676985, "min": 0.0005063527925952071, "max": 0.014768443167120273, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2008103999547779, "min": 0.005063527925952071, "max": 0.22047788667259735, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5394923440119048e-06, "min": 1.5394923440119048e-06, "max": 0.00029825595058135, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1552892816166667e-05, "min": 2.1552892816166667e-05, "max": 0.0039826897724368, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051313095238099, "min": 0.10051313095238099, "max": 0.19941865000000003, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071838333333337, "min": 1.4071838333333337, "max": 2.8275632000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.126178214285714e-05, "min": 6.126178214285714e-05, "max": 0.009941923134999999, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00085766495, "min": 0.00085766495, "max": 0.13277356368, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00356890051625669, "min": 0.00322205713018775, "max": 0.5150662064552307, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.04996460676193237, "min": 0.045339301228523254, "max": 4.120529651641846, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.029702970297, "min": 261.3636363636364, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30202.0, "min": 16830.0, "max": 33054.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6436279855668545, "min": -0.9999936006722911, "max": 1.7279428409678594, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 164.36279855668545, "min": -31.998801663517952, "max": 190.95899880677462, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6436279855668545, "min": -0.9999936006722911, "max": 1.7279428409678594, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 164.36279855668545, "min": -31.998801663517952, "max": 190.95899880677462, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011405315355223138, "min": 0.009599362899020239, "max": 9.803752701315615, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1405315355223138, "min": 0.9823717609469895, "max": 176.46754862368107, "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": "1718342867", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718349708" }, "total": 6841.161636041001, "count": 1, "self": 0.4872589370006608, "children": { "run_training.setup": { "total": 0.05256336399997963, "count": 1, "self": 0.05256336399997963 }, "TrainerController.start_learning": { "total": 6840.62181374, "count": 1, "self": 4.420374444945082, "children": { "TrainerController._reset_env": { "total": 2.7054285859999254, "count": 1, "self": 2.7054285859999254 }, "TrainerController.advance": { "total": 6833.406581944057, "count": 193224, "self": 4.370507500056192, "children": { "env_step": { "total": 4895.960554215204, "count": 193224, "self": 4493.7974473933355, "children": { "SubprocessEnvManager._take_step": { "total": 399.6064107479606, "count": 193224, "self": 14.57937543988146, "children": { "TorchPolicy.evaluate": { "total": 385.0270353080791, "count": 187560, "self": 385.0270353080791 } } }, "workers": { "total": 2.556696073907915, "count": 193224, "self": 0.0, "children": { "worker_root": { "total": 6824.726432563747, "count": 193224, "is_parallel": true, "self": 2709.208436832617, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002036199000031047, "count": 1, "is_parallel": true, "self": 0.0005990040001506713, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014371949998803757, "count": 8, "is_parallel": true, "self": 0.0014371949998803757 } } }, "UnityEnvironment.step": { "total": 0.09134857499998361, "count": 1, "is_parallel": true, "self": 0.000657079999882626, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004412640000737156, "count": 1, "is_parallel": true, "self": 0.0004412640000737156 }, "communicator.exchange": { "total": 0.08856951799998569, "count": 1, "is_parallel": true, "self": 0.08856951799998569 }, "steps_from_proto": { "total": 0.0016807130000415782, "count": 1, "is_parallel": true, "self": 0.00035088499998892075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013298280000526574, "count": 8, "is_parallel": true, "self": 0.0013298280000526574 } } } } } } }, "UnityEnvironment.step": { "total": 4115.51799573113, "count": 193223, "is_parallel": true, "self": 102.954349190004, "children": { "UnityEnvironment._generate_step_input": { "total": 68.84359439720015, "count": 193223, "is_parallel": true, "self": 68.84359439720015 }, "communicator.exchange": { "total": 3649.930098685735, "count": 193223, "is_parallel": true, "self": 3649.930098685735 }, "steps_from_proto": { "total": 293.78995345819135, "count": 193223, "is_parallel": true, "self": 60.11245441422602, "children": { "_process_rank_one_or_two_observation": { "total": 233.67749904396533, "count": 1545784, "is_parallel": true, "self": 233.67749904396533 } } } } } } } } } } }, "trainer_advance": { "total": 1933.0755202287964, "count": 193224, "self": 8.675076898777661, "children": { "process_trajectory": { "total": 393.49766867800645, "count": 193224, "self": 392.6471074710071, "children": { "RLTrainer._checkpoint": { "total": 0.8505612069993731, "count": 6, "self": 0.8505612069993731 } } }, "_update_policy": { "total": 1530.9027746520123, "count": 1385, "self": 907.8751228748786, "children": { "TorchPPOOptimizer.update": { "total": 623.0276517771338, "count": 68343, "self": 623.0276517771338 } } } } } } }, "trainer_threads": { "total": 8.719998731976375e-07, "count": 1, "self": 8.719998731976375e-07 }, "TrainerController._save_models": { "total": 0.08942789299908327, "count": 1, "self": 0.0017322319999948377, "children": { "RLTrainer._checkpoint": { "total": 0.08769566099908843, "count": 1, "self": 0.08769566099908843 } } } } } } }