{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42515310645103455, "min": 0.42515310645103455, "max": 1.5253571271896362, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12795.408203125, "min": 12772.572265625, "max": 46273.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5576751828193665, "min": -0.07953717559576035, "max": 0.5576751828193665, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.57229614257812, "min": -19.08892250061035, "max": 153.28184509277344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011278037913143635, "min": -0.0038831362035125494, "max": 0.16918087005615234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.045070171356201, "min": -0.9824334383010864, "max": 40.77259063720703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06889286694266568, "min": 0.0655785342094313, "max": 0.07343669621462519, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9645001371973194, "min": 0.4810857835256537, "max": 1.0372896594926715, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012016281686859049, "min": 0.0010588723298317945, "max": 0.01383227568918041, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1682279436160267, "min": 0.011009864221108907, "max": 0.20479924480605408, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.677590297978573e-06, "min": 7.677590297978573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010748626417170001, "min": 0.00010748626417170001, "max": 0.0035070803309733, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255916428571431, "min": 0.10255916428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358283000000003, "min": 1.3886848, "max": 2.5690267, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002656605121428571, "min": 0.0002656605121428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00371924717, "min": 0.00371924717, "max": 0.11692576733000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005452931392937899, "min": 0.005452931392937899, "max": 0.23675133287906647, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07634104043245316, "min": 0.07634104043245316, "max": 1.6572593450546265, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 355.70666666666665, "min": 355.70666666666665, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26678.0, "min": 15984.0, "max": 33765.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5642693132162093, "min": -1.0000000521540642, "max": 1.5984916471772723, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.3201984912157, "min": -30.660001680254936, "max": 129.86599806696177, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5642693132162093, "min": -1.0000000521540642, "max": 1.5984916471772723, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.3201984912157, "min": -30.660001680254936, "max": 129.86599806696177, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.020347743295521165, "min": 0.020347743295521165, "max": 4.793652108870447, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5260807471640874, "min": 1.5260807471640874, "max": 76.69843374192715, "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": "1784811829", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/mlagents310/bin/mlagents-learn ./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": "1784814208" }, "total": 2378.702976746, "count": 1, "self": 0.5345754950003538, "children": { "run_training.setup": { "total": 0.024211465000007593, "count": 1, "self": 0.024211465000007593 }, "TrainerController.start_learning": { "total": 2378.1441897859995, "count": 1, "self": 1.3798230809770757, "children": { "TrainerController._reset_env": { "total": 4.011365844000011, "count": 1, "self": 4.011365844000011 }, "TrainerController.advance": { "total": 2372.671495831022, "count": 63681, "self": 1.418634057019517, "children": { "env_step": { "total": 1741.9638882970055, "count": 63681, "self": 1587.0852678200827, "children": { "SubprocessEnvManager._take_step": { "total": 154.0586643969632, "count": 63681, "self": 4.754833269970959, "children": { "TorchPolicy.evaluate": { "total": 149.30383112699224, "count": 62558, "self": 149.30383112699224 } } }, "workers": { "total": 0.8199560799596384, "count": 63681, "self": 0.0, "children": { "worker_root": { "total": 2372.0018041089343, "count": 63681, "is_parallel": true, "self": 904.3139379338895, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005281754999941768, "count": 1, "is_parallel": true, "self": 0.003545701000120971, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017360539998207969, "count": 8, "is_parallel": true, "self": 0.0017360539998207969 } } }, "UnityEnvironment.step": { "total": 0.053656971000009435, "count": 1, "is_parallel": true, "self": 0.0006093930001043191, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005032669998854544, "count": 1, "is_parallel": true, "self": 0.0005032669998854544 }, "communicator.exchange": { "total": 0.050807308000003104, "count": 1, "is_parallel": true, "self": 0.050807308000003104 }, "steps_from_proto": { "total": 0.001737003000016557, "count": 1, "is_parallel": true, "self": 0.00037772399969071557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013592790003258415, "count": 8, "is_parallel": true, "self": 0.0013592790003258415 } } } } } } }, "UnityEnvironment.step": { "total": 1467.6878661750447, "count": 63680, "is_parallel": true, "self": 34.84616297302841, "children": { "UnityEnvironment._generate_step_input": { "total": 23.853537305000145, "count": 63680, "is_parallel": true, "self": 23.853537305000145 }, "communicator.exchange": { "total": 1299.153024470994, "count": 63680, "is_parallel": true, "self": 1299.153024470994 }, "steps_from_proto": { "total": 109.83514142602212, "count": 63680, "is_parallel": true, "self": 22.689049802905174, "children": { "_process_rank_one_or_two_observation": { "total": 87.14609162311694, "count": 509440, "is_parallel": true, "self": 87.14609162311694 } } } } } } } } } } }, "trainer_advance": { "total": 629.2889734769972, "count": 63681, "self": 2.6136029169440462, "children": { "process_trajectory": { "total": 110.87042127705786, "count": 63681, "self": 110.62012147705786, "children": { "RLTrainer._checkpoint": { "total": 0.2502997999999934, "count": 2, "self": 0.2502997999999934 } } }, "_update_policy": { "total": 515.8049492829953, "count": 448, "self": 275.2486320830551, "children": { "TorchPPOOptimizer.update": { "total": 240.55631719994017, "count": 22773, "self": 240.55631719994017 } } } } } } }, "trainer_threads": { "total": 1.0819999261002522e-06, "count": 1, "self": 1.0819999261002522e-06 }, "TrainerController._save_models": { "total": 0.0815039480003179, "count": 1, "self": 0.0010004750001826324, "children": { "RLTrainer._checkpoint": { "total": 0.08050347300013527, "count": 1, "self": 0.08050347300013527 } } } } } } }