{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29054930806159973, "min": 0.23329854011535645, "max": 1.3596144914627075, "count": 122 }, "Pyramids.Policy.Entropy.sum": { "value": 8595.6103515625, "min": 7028.818359375, "max": 41245.265625, "count": 122 }, "Pyramids.Step.mean": { "value": 3659882.0, "min": 29931.0, "max": 3659882.0, "count": 122 }, "Pyramids.Step.sum": { "value": 3659882.0, "min": 29931.0, "max": 3659882.0, "count": 122 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8309521675109863, "min": -0.14771369099617004, "max": 0.8955442309379578, "count": 122 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 256.76422119140625, "min": -35.5989990234375, "max": 277.61871337890625, "count": 122 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005796498153358698, "min": -0.020980294793844223, "max": 0.4695992171764374, "count": 122 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7911179065704346, "min": -6.252127647399902, "max": 111.29501342773438, "count": 122 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06827977287632944, "min": 0.06430021362307127, "max": 0.08033802269797195, "count": 122 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9559168202686122, "min": 0.5681599113328735, "max": 1.1247323177716073, "count": 122 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015933373510571464, "min": 0.00048440896773078735, "max": 0.01664026495598678, "count": 122 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2230672291480005, "min": 0.006781725548231023, "max": 0.23296370938381492, "count": 122 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019066262573151784, "min": 0.00019066262573151784, "max": 0.00029948420642193123, "count": 122 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0026692767602412497, "min": 0.00239587365137545, "max": 0.004344843051718999, "count": 122 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16355419642857144, "min": 0.16355419642857144, "max": 0.19982806875000003, "count": 122 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2897587500000003, "min": 1.5986245500000003, "max": 2.9482809999999997, "count": 122 }, "Pyramids.Policy.Beta.mean": { "value": 0.006359064223214286, "min": 0.006359064223214286, "max": 0.009982824068125, "count": 122 }, "Pyramids.Policy.Beta.sum": { "value": 0.089026899125, "min": 0.079862592545, "max": 0.14483327189999998, "count": 122 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005936332046985626, "min": 0.004931471310555935, "max": 0.4128558039665222, "count": 122 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08310864865779877, "min": 0.06904059648513794, "max": 3.3028464317321777, "count": 122 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 219.70422535211267, "min": 209.50335570469798, "max": 999.0, "count": 122 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31198.0, "min": 17241.0, "max": 33288.0, "count": 122 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7662042135398992, "min": -0.9998375526629388, "max": 1.7904966305566314, "count": 122 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 250.8009983226657, "min": -31.994801685214043, "max": 266.7839979529381, "count": 122 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7662042135398992, "min": -0.9998375526629388, "max": 1.7904966305566314, "count": 122 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 250.8009983226657, "min": -31.994801685214043, "max": 266.7839979529381, "count": 122 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013619337259665949, "min": 0.012362895060184254, "max": 7.913583682643043, "count": 122 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9339458908725646, "min": 1.4416112098260783, "max": 142.44450628757477, "count": 122 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 122 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 122 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739869001", "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": "1739878292" }, "total": 9291.524195393, "count": 1, "self": 0.43623197300075844, "children": { "run_training.setup": { "total": 0.020223127999997814, "count": 1, "self": 0.020223127999997814 }, "TrainerController.start_learning": { "total": 9291.067740292, "count": 1, "self": 5.804042537143687, "children": { "TrainerController._reset_env": { "total": 2.1362516149997646, "count": 1, "self": 2.1362516149997646 }, "TrainerController.advance": { "total": 9282.989205800854, "count": 238432, "self": 6.2579750178319955, "children": { "env_step": { "total": 6747.465627329957, "count": 238432, "self": 6151.05580353647, "children": { "SubprocessEnvManager._take_step": { "total": 592.8423387924167, "count": 238432, "self": 18.244956292917777, "children": { "TorchPolicy.evaluate": { "total": 574.597382499499, "count": 229194, "self": 574.597382499499 } } }, "workers": { "total": 3.567485001069599, "count": 238431, "self": 0.0, "children": { "worker_root": { "total": 9271.431817764855, "count": 238431, "is_parallel": true, "self": 3567.7752929374146, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002045645999714907, "count": 1, "is_parallel": true, "self": 0.0006433420003304491, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014023039993844577, "count": 8, "is_parallel": true, "self": 0.0014023039993844577 } } }, "UnityEnvironment.step": { "total": 0.049226441999962844, "count": 1, "is_parallel": true, "self": 0.0005485129995577154, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004293410001992015, "count": 1, "is_parallel": true, "self": 0.0004293410001992015 }, "communicator.exchange": { "total": 0.04660117299999911, "count": 1, "is_parallel": true, "self": 0.04660117299999911 }, "steps_from_proto": { "total": 0.00164741500020682, "count": 1, "is_parallel": true, "self": 0.00035003499942831695, "children": { "_process_rank_one_or_two_observation": { "total": 0.001297380000778503, "count": 8, "is_parallel": true, "self": 0.001297380000778503 } } } } } } }, "UnityEnvironment.step": { "total": 5703.65652482744, "count": 238430, "is_parallel": true, "self": 120.29463871310145, "children": { "UnityEnvironment._generate_step_input": { "total": 85.7308391218885, "count": 238430, "is_parallel": true, "self": 85.7308391218885 }, "communicator.exchange": { "total": 5130.3556073194, "count": 238430, "is_parallel": true, "self": 5130.3556073194 }, "steps_from_proto": { "total": 367.2754396730493, "count": 238430, "is_parallel": true, "self": 77.79098153192172, "children": { "_process_rank_one_or_two_observation": { "total": 289.48445814112756, "count": 1907440, "is_parallel": true, "self": 289.48445814112756 } } } } } } } } } } }, "trainer_advance": { "total": 2529.2656034530646, "count": 238431, "self": 11.475616490120501, "children": { "process_trajectory": { "total": 493.2178023559363, "count": 238431, "self": 492.2649174819371, "children": { "RLTrainer._checkpoint": { "total": 0.95288487399921, "count": 7, "self": 0.95288487399921 } } }, "_update_policy": { "total": 2024.5721846070078, "count": 1722, "self": 1103.3897381675624, "children": { "TorchPPOOptimizer.update": { "total": 921.1824464394454, "count": 83589, "self": 921.1824464394454 } } } } } } }, "trainer_threads": { "total": 1.341000825050287e-06, "count": 1, "self": 1.341000825050287e-06 }, "TrainerController._save_models": { "total": 0.13823899800081563, "count": 1, "self": 0.002238256001874106, "children": { "RLTrainer._checkpoint": { "total": 0.13600074199894152, "count": 1, "self": 0.13600074199894152 } } } } } } }