{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9259867668151855, "min": 0.8769648671150208, "max": 0.9259867668151855, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 27735.15625, "min": 17623.486328125, "max": 27735.15625, "count": 3 }, "Pyramids.Step.mean": { "value": 179921.0, "min": 119888.0, "max": 179921.0, "count": 3 }, "Pyramids.Step.sum": { "value": 179921.0, "min": 119888.0, "max": 179921.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09521700441837311, "min": -0.10461809486150742, "max": -0.09216971695423126, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -22.852081298828125, "min": -22.852081298828125, "max": -16.529659271240234, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06673477590084076, "min": 0.06673477590084076, "max": 0.10928431898355484, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.016345977783203, "min": 16.016345977783203, "max": 23.216726303100586, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06650441241170575, "min": 0.06650441241170575, "max": 0.07030591471725726, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.798052948940469, "min": 0.2801994997298816, "max": 0.798052948940469, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00017486471076749626, "min": 0.00017486471076749626, "max": 0.0013649598767580102, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0020983765292099553, "min": 0.0020983765292099553, "max": 0.0136495987675801, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.34945821685e-05, "min": 5.34945821685e-05, "max": 0.00013471205509600002, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000641934986022, "min": 0.0005388482203840001, "max": 0.000982176672608, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11783150000000002, "min": 0.11783150000000002, "max": 0.144904, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4139780000000002, "min": 0.579616, "max": 1.4139780000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0017913668500000007, "min": 0.0017913668500000007, "max": 0.0044959096, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.021496402200000007, "min": 0.0179836384, "max": 0.0328064608, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.05180659890174866, "min": 0.05180659890174866, "max": 0.07853716611862183, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.6216791868209839, "min": 0.3141486644744873, "max": 0.6216791868209839, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 998.28125, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31968.0, "min": 15984.0, "max": 31968.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9999484393385148, "min": -1.0000000521540642, "max": -0.8741938006132841, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.99840161949396, "min": -30.99840161949396, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9999484393385148, "min": -1.0000000521540642, "max": -0.8741938006132841, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.99840161949396, "min": -30.99840161949396, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 0.534257584281506, "min": 0.534257584281506, "max": 0.8186110365204513, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 16.56198511272669, "min": 13.097776584327221, "max": 19.85759885981679, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1782636950", "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 --resume", "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": "1782637165" }, "total": 214.87066589799997, "count": 1, "self": 0.4798725320001722, "children": { "run_training.setup": { "total": 0.02424729899985323, "count": 1, "self": 0.02424729899985323 }, "TrainerController.start_learning": { "total": 214.36654606699994, "count": 1, "self": 0.13467098800947497, "children": { "TrainerController._reset_env": { "total": 2.1855458589998307, "count": 1, "self": 2.1855458589998307 }, "TrainerController.advance": { "total": 211.81623517799062, "count": 6266, "self": 0.1456589550134595, "children": { "env_step": { "total": 150.42087508299892, "count": 6266, "self": 134.77207955304357, "children": { "SubprocessEnvManager._take_step": { "total": 15.566905309963659, "count": 6266, "self": 0.4703167549682803, "children": { "TorchPolicy.evaluate": { "total": 15.096588554995378, "count": 6256, "self": 15.096588554995378 } } }, "workers": { "total": 0.08189021999169199, "count": 6266, "self": 0.0, "children": { "worker_root": { "total": 213.42091515801076, "count": 6266, "is_parallel": true, "self": 90.6735544820267, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017912769999384182, "count": 1, "is_parallel": true, "self": 0.0006375309994837153, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011537460004547029, "count": 8, "is_parallel": true, "self": 0.0011537460004547029 } } }, "UnityEnvironment.step": { "total": 0.05034289000013814, "count": 1, "is_parallel": true, "self": 0.0005745249995925406, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046643500036225305, "count": 1, "is_parallel": true, "self": 0.00046643500036225305 }, "communicator.exchange": { "total": 0.04747408399998676, "count": 1, "is_parallel": true, "self": 0.04747408399998676 }, "steps_from_proto": { "total": 0.0018278460001965868, "count": 1, "is_parallel": true, "self": 0.0003568780002751737, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014709679999214131, "count": 8, "is_parallel": true, "self": 0.0014709679999214131 } } } } } } }, "UnityEnvironment.step": { "total": 122.74736067598405, "count": 6265, "is_parallel": true, "self": 3.4582741830149644, "children": { "UnityEnvironment._generate_step_input": { "total": 2.3929653799882544, "count": 6265, "is_parallel": true, "self": 2.3929653799882544 }, "communicator.exchange": { "total": 105.69274092498563, "count": 6265, "is_parallel": true, "self": 105.69274092498563 }, "steps_from_proto": { "total": 11.203380187995208, "count": 6265, "is_parallel": true, "self": 2.374361956912253, "children": { "_process_rank_one_or_two_observation": { "total": 8.829018231082955, "count": 50120, "is_parallel": true, "self": 8.829018231082955 } } } } } } } } } } }, "trainer_advance": { "total": 61.24970113997824, "count": 6266, "self": 0.19105842799581296, "children": { "process_trajectory": { "total": 10.351301033983873, "count": 6266, "self": 10.351301033983873 }, "_update_policy": { "total": 50.707341677998556, "count": 33, "self": 27.28086230200597, "children": { "TorchPPOOptimizer.update": { "total": 23.426479375992585, "count": 2283, "self": 23.426479375992585 } } } } } } }, "trainer_threads": { "total": 8.679999154992402e-07, "count": 1, "self": 8.679999154992402e-07 }, "TrainerController._save_models": { "total": 0.23009317400010332, "count": 1, "self": 0.001246918000106234, "children": { "RLTrainer._checkpoint": { "total": 0.22884625599999708, "count": 1, "self": 0.22884625599999708 } } } } } } }