{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4486292600631714, "min": 0.446056991815567, "max": 1.4883973598480225, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13415.8095703125, "min": 13407.033203125, "max": 45152.0234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6434611082077026, "min": -0.09321875125169754, "max": 0.6892572641372681, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 181.45602416992188, "min": -22.558937072753906, "max": 197.81683349609375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013277684338390827, "min": -0.004010356497019529, "max": 0.16979658603668213, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.744307041168213, "min": -1.0787858963012695, "max": 40.92097854614258, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06623327902331362, "min": 0.06463872416963724, "max": 0.07349589960843636, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9272659063263906, "min": 0.508184837572472, "max": 1.032997850719588, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014775744885578297, "min": 0.00024180679733388778, "max": 0.017115614010738987, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20686042839809615, "min": 0.0026598747706727656, "max": 0.2396185961503458, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5859403285285725e-06, "min": 7.5859403285285725e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010620316459940001, "min": 0.00010620316459940001, "max": 0.0032546039151320994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252861428571428, "min": 0.10252861428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354006, "min": 1.3886848, "max": 2.4435772, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002626085671428572, "min": 0.0002626085671428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036765199400000006, "min": 0.0036765199400000006, "max": 0.10850830321000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010439842008054256, "min": 0.010181385092437267, "max": 0.34395018219947815, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14615778625011444, "min": 0.1425393968820572, "max": 2.40765118598938, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 303.2970297029703, "min": 263.7543859649123, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30633.0, "min": 15984.0, "max": 33517.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6146219815313816, "min": -1.0000000521540642, "max": 1.7186999858209961, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 161.46219815313816, "min": -31.998401656746864, "max": 195.93179838359356, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6146219815313816, "min": -1.0000000521540642, "max": 1.7186999858209961, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 161.46219815313816, "min": -31.998401656746864, "max": 195.93179838359356, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03309669010050129, "min": 0.02850342443816133, "max": 6.798176889307797, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.309669010050129, "min": 2.789618145325221, "max": 108.77083022892475, "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": "1740767249", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740769473" }, "total": 2223.989839283, "count": 1, "self": 0.4923828269998012, "children": { "run_training.setup": { "total": 0.020123630999933084, "count": 1, "self": 0.020123630999933084 }, "TrainerController.start_learning": { "total": 2223.4773328250003, "count": 1, "self": 1.3218328370139716, "children": { "TrainerController._reset_env": { "total": 2.4105610039998737, "count": 1, "self": 2.4105610039998737 }, "TrainerController.advance": { "total": 2219.6593951809864, "count": 64070, "self": 1.3252972231052809, "children": { "env_step": { "total": 1538.240079701921, "count": 64070, "self": 1387.9818864189613, "children": { "SubprocessEnvManager._take_step": { "total": 149.4423519909608, "count": 64070, "self": 4.495108517915014, "children": { "TorchPolicy.evaluate": { "total": 144.94724347304577, "count": 62568, "self": 144.94724347304577 } } }, "workers": { "total": 0.8158412919990496, "count": 64070, "self": 0.0, "children": { "worker_root": { "total": 2218.3380603049955, "count": 64070, "is_parallel": true, "self": 940.4707170999795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001940980999961539, "count": 1, "is_parallel": true, "self": 0.0006185359993651218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013224450005964172, "count": 8, "is_parallel": true, "self": 0.0013224450005964172 } } }, "UnityEnvironment.step": { "total": 0.06272158399997352, "count": 1, "is_parallel": true, "self": 0.0005932169999596226, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004544349999378028, "count": 1, "is_parallel": true, "self": 0.0004544349999378028 }, "communicator.exchange": { "total": 0.059932549999984985, "count": 1, "is_parallel": true, "self": 0.059932549999984985 }, "steps_from_proto": { "total": 0.0017413820000911073, "count": 1, "is_parallel": true, "self": 0.0003851780004424654, "children": { "_process_rank_one_or_two_observation": { "total": 0.001356203999648642, "count": 8, "is_parallel": true, "self": 0.001356203999648642 } } } } } } }, "UnityEnvironment.step": { "total": 1277.867343205016, "count": 64069, "is_parallel": true, "self": 31.205285166131944, "children": { "UnityEnvironment._generate_step_input": { "total": 22.47402749003254, "count": 64069, "is_parallel": true, "self": 22.47402749003254 }, "communicator.exchange": { "total": 1131.62827197993, "count": 64069, "is_parallel": true, "self": 1131.62827197993 }, "steps_from_proto": { "total": 92.55975856892132, "count": 64069, "is_parallel": true, "self": 18.244768820989748, "children": { "_process_rank_one_or_two_observation": { "total": 74.31498974793158, "count": 512552, "is_parallel": true, "self": 74.31498974793158 } } } } } } } } } } }, "trainer_advance": { "total": 680.09401825596, "count": 64070, "self": 2.54840008393694, "children": { "process_trajectory": { "total": 127.68775831801781, "count": 64070, "self": 127.48682037501771, "children": { "RLTrainer._checkpoint": { "total": 0.20093794300009904, "count": 2, "self": 0.20093794300009904 } } }, "_update_policy": { "total": 549.8578598540053, "count": 450, "self": 301.8309022210135, "children": { "TorchPPOOptimizer.update": { "total": 248.02695763299175, "count": 22797, "self": 248.02695763299175 } } } } } } }, "trainer_threads": { "total": 8.130000423989259e-07, "count": 1, "self": 8.130000423989259e-07 }, "TrainerController._save_models": { "total": 0.08554299000024912, "count": 1, "self": 0.0016201360003833543, "children": { "RLTrainer._checkpoint": { "total": 0.08392285399986577, "count": 1, "self": 0.08392285399986577 } } } } } } }