{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37931501865386963, "min": 0.37931501865386963, "max": 1.4356695413589478, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11519.0380859375, "min": 11488.189453125, "max": 43552.47265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29903.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29903.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6160839796066284, "min": -0.10576646029949188, "max": 0.6504782438278198, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.20001220703125, "min": -25.489717483520508, "max": 188.63868713378906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0023723181802779436, "min": -0.023880835622549057, "max": 0.40277382731437683, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.6784830093383789, "min": -6.2806596755981445, "max": 95.4573974609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06576063543547034, "min": 0.06444122273976627, "max": 0.07404839421177725, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9206488960965847, "min": 0.5183387594824408, "max": 1.0636327762222921, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01671217508070792, "min": 0.00041937753764921185, "max": 0.018361406066554082, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23397045112991086, "min": 0.0037743978388429067, "max": 0.27240155329733773, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.693768864014286e-06, "min": 7.693768864014286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010771276409620001, "min": 0.00010771276409620001, "max": 0.0035079317306895, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256455714285714, "min": 0.10256455714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359038, "min": 1.3886848, "max": 2.6625277, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002661992585714287, "min": 0.0002661992585714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037267896200000017, "min": 0.0037267896200000017, "max": 0.11695411894999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010105631314218044, "min": 0.010105631314218044, "max": 0.35911989212036133, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14147883653640747, "min": 0.14147883653640747, "max": 2.5138392448425293, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 302.53921568627453, "min": 293.4757281553398, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30859.0, "min": 16830.0, "max": 32982.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.69635642032222, "min": -1.0000000521540642, "max": 1.69635642032222, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.3319984525442, "min": -32.000001668930054, "max": 171.3319984525442, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.69635642032222, "min": -1.0000000521540642, "max": 1.69635642032222, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.3319984525442, "min": -32.000001668930054, "max": 171.3319984525442, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03191587889159564, "min": 0.031087937423418553, "max": 6.286493404823191, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2235037680511596, "min": 3.151987976489181, "max": 106.87038788199425, "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": "1698262506", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698264892" }, "total": 2385.5449966209994, "count": 1, "self": 0.5262584829993102, "children": { "run_training.setup": { "total": 0.04622457899995425, "count": 1, "self": 0.04622457899995425 }, "TrainerController.start_learning": { "total": 2384.972513559, "count": 1, "self": 1.5940617879159618, "children": { "TrainerController._reset_env": { "total": 3.5643994729998667, "count": 1, "self": 3.5643994729998667 }, "TrainerController.advance": { "total": 2379.731835599084, "count": 64115, "self": 1.594001031112839, "children": { "env_step": { "total": 1735.5803722039386, "count": 64115, "self": 1593.434857382861, "children": { "SubprocessEnvManager._take_step": { "total": 141.19756557018945, "count": 64115, "self": 4.9891576851237005, "children": { "TorchPolicy.evaluate": { "total": 136.20840788506575, "count": 62551, "self": 136.20840788506575 } } }, "workers": { "total": 0.9479492508880867, "count": 64115, "self": 0.0, "children": { "worker_root": { "total": 2379.8468308858405, "count": 64115, "is_parallel": true, "self": 908.7819385949042, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018776850001813727, "count": 1, "is_parallel": true, "self": 0.0005979749998914485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012797100002899242, "count": 8, "is_parallel": true, "self": 0.0012797100002899242 } } }, "UnityEnvironment.step": { "total": 0.05231575800007704, "count": 1, "is_parallel": true, "self": 0.0005716440000469447, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004881510003542644, "count": 1, "is_parallel": true, "self": 0.0004881510003542644 }, "communicator.exchange": { "total": 0.049529531999723986, "count": 1, "is_parallel": true, "self": 0.049529531999723986 }, "steps_from_proto": { "total": 0.0017264309999518446, "count": 1, "is_parallel": true, "self": 0.00037407599984362605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013523550001082185, "count": 8, "is_parallel": true, "self": 0.0013523550001082185 } } } } } } }, "UnityEnvironment.step": { "total": 1471.0648922909363, "count": 64114, "is_parallel": true, "self": 36.24249428485746, "children": { "UnityEnvironment._generate_step_input": { "total": 24.42519154521915, "count": 64114, "is_parallel": true, "self": 24.42519154521915 }, "communicator.exchange": { "total": 1309.3580496230047, "count": 64114, "is_parallel": true, "self": 1309.3580496230047 }, "steps_from_proto": { "total": 101.03915683785499, "count": 64114, "is_parallel": true, "self": 20.932430413078237, "children": { "_process_rank_one_or_two_observation": { "total": 80.10672642477675, "count": 512912, "is_parallel": true, "self": 80.10672642477675 } } } } } } } } } } }, "trainer_advance": { "total": 642.5574623640327, "count": 64115, "self": 2.928210118009247, "children": { "process_trajectory": { "total": 124.28750345502658, "count": 64115, "self": 124.10867306602677, "children": { "RLTrainer._checkpoint": { "total": 0.1788303889998133, "count": 2, "self": 0.1788303889998133 } } }, "_update_policy": { "total": 515.3417487909969, "count": 449, "self": 307.34143334690134, "children": { "TorchPPOOptimizer.update": { "total": 208.00031544409558, "count": 22818, "self": 208.00031544409558 } } } } } } }, "trainer_threads": { "total": 1.050999344442971e-06, "count": 1, "self": 1.050999344442971e-06 }, "TrainerController._save_models": { "total": 0.0822156480007834, "count": 1, "self": 0.001768110000739398, "children": { "RLTrainer._checkpoint": { "total": 0.080447538000044, "count": 1, "self": 0.080447538000044 } } } } } } }