{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3553622364997864, "min": 0.3292371928691864, "max": 1.3780255317687988, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10768.8974609375, "min": 9882.3837890625, "max": 41803.78125, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29915.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29915.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.701176643371582, "min": -0.08960031718015671, "max": 0.7213871479034424, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 206.84710693359375, "min": -21.683277130126953, "max": 213.5305938720703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0086286012083292, "min": -0.005355819594115019, "max": 0.4184195101261139, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5454373359680176, "min": -1.4996294975280762, "max": 99.16542053222656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07156671694703583, "min": 0.06400450659807053, "max": 0.07385286327860063, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0019340372585015, "min": 0.5054248289334596, "max": 1.0582794581783033, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01801811614307296, "min": 0.00043296472886908893, "max": 0.01801811614307296, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2522536260030214, "min": 0.005628541475298156, "max": 0.2522536260030214, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.729275995035714e-06, "min": 7.729275995035714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010820986393050001, "min": 0.00010820986393050001, "max": 0.003632241189253, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257639285714286, "min": 0.10257639285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360695, "min": 1.3886848, "max": 2.6107470000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026738164642857144, "min": 0.00026738164642857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00374334305, "min": 0.00374334305, "max": 0.12109362530000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010969838127493858, "min": 0.010969838127493858, "max": 0.45114240050315857, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15357773005962372, "min": 0.15357773005962372, "max": 3.157996892929077, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 267.66386554621846, "min": 256.73275862068965, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31852.0, "min": 16842.0, "max": 33011.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6992520813931937, "min": -0.9999871489501768, "max": 1.7406880605384845, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 202.21099768579006, "min": -30.999601617455482, "max": 202.21099768579006, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6992520813931937, "min": -0.9999871489501768, "max": 1.7406880605384845, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 202.21099768579006, "min": -30.999601617455482, "max": 202.21099768579006, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030625398024687243, "min": 0.029938262647002653, "max": 9.25762802362442, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.644422364937782, "min": 3.442900204405305, "max": 157.37967640161514, "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": "1709060549", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709062759" }, "total": 2210.2115979, "count": 1, "self": 0.9010030470003585, "children": { "run_training.setup": { "total": 0.051689949999854434, "count": 1, "self": 0.051689949999854434 }, "TrainerController.start_learning": { "total": 2209.258904903, "count": 1, "self": 1.3288486260166792, "children": { "TrainerController._reset_env": { "total": 2.4321096779999607, "count": 1, "self": 2.4321096779999607 }, "TrainerController.advance": { "total": 2205.384784044983, "count": 64170, "self": 1.4252789349511659, "children": { "env_step": { "total": 1582.5691336279178, "count": 64170, "self": 1458.170665863824, "children": { "SubprocessEnvManager._take_step": { "total": 123.59485966600369, "count": 64170, "self": 4.586933456974293, "children": { "TorchPolicy.evaluate": { "total": 119.00792620902939, "count": 62576, "self": 119.00792620902939 } } }, "workers": { "total": 0.8036080980900806, "count": 64170, "self": 0.0, "children": { "worker_root": { "total": 2204.2312615840156, "count": 64170, "is_parallel": true, "self": 857.9710342650251, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021462300001076073, "count": 1, "is_parallel": true, "self": 0.0006898850006109569, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014563449994966504, "count": 8, "is_parallel": true, "self": 0.0014563449994966504 } } }, "UnityEnvironment.step": { "total": 0.04850034900027822, "count": 1, "is_parallel": true, "self": 0.0005753730001742952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005049950000284298, "count": 1, "is_parallel": true, "self": 0.0005049950000284298 }, "communicator.exchange": { "total": 0.04578265999998621, "count": 1, "is_parallel": true, "self": 0.04578265999998621 }, "steps_from_proto": { "total": 0.0016373210000892868, "count": 1, "is_parallel": true, "self": 0.0003382970007805852, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012990239993087016, "count": 8, "is_parallel": true, "self": 0.0012990239993087016 } } } } } } }, "UnityEnvironment.step": { "total": 1346.2602273189905, "count": 64169, "is_parallel": true, "self": 34.70479730099305, "children": { "UnityEnvironment._generate_step_input": { "total": 24.104658128037954, "count": 64169, "is_parallel": true, "self": 24.104658128037954 }, "communicator.exchange": { "total": 1190.4014419869427, "count": 64169, "is_parallel": true, "self": 1190.4014419869427 }, "steps_from_proto": { "total": 97.04932990301677, "count": 64169, "is_parallel": true, "self": 18.97622890274306, "children": { "_process_rank_one_or_two_observation": { "total": 78.07310100027371, "count": 513352, "is_parallel": true, "self": 78.07310100027371 } } } } } } } } } } }, "trainer_advance": { "total": 621.390371482114, "count": 64170, "self": 2.5299614221135016, "children": { "process_trajectory": { "total": 125.6553079109949, "count": 64170, "self": 125.42975579299491, "children": { "RLTrainer._checkpoint": { "total": 0.22555211799999597, "count": 2, "self": 0.22555211799999597 } } }, "_update_policy": { "total": 493.2051021490056, "count": 454, "self": 288.62239076202013, "children": { "TorchPPOOptimizer.update": { "total": 204.58271138698547, "count": 22824, "self": 204.58271138698547 } } } } } } }, "trainer_threads": { "total": 1.2840000636060722e-06, "count": 1, "self": 1.2840000636060722e-06 }, "TrainerController._save_models": { "total": 0.11316127000009146, "count": 1, "self": 0.0021574350002993015, "children": { "RLTrainer._checkpoint": { "total": 0.11100383499979216, "count": 1, "self": 0.11100383499979216 } } } } } } }