{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15252816677093506, "min": 0.14906516671180725, "max": 1.414180874824524, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4588.04736328125, "min": 4464.7998046875, "max": 42900.58984375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999890.0, "min": 29952.0, "max": 2999890.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999890.0, "min": 29952.0, "max": 2999890.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8182879686355591, "min": -0.1800912469625473, "max": 0.8639610409736633, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 252.85098266601562, "min": -42.68162536621094, "max": 264.73980712890625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01633444055914879, "min": -0.01727745309472084, "max": 0.46886947751045227, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.047342300415039, "min": -4.9931840896606445, "max": 111.12206268310547, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06845543435645393, "min": 0.06536668095607585, "max": 0.07368367805766238, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.026831515346809, "min": 0.49879954672351967, "max": 1.092246385746608, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016203644212024904, "min": 0.0006459115332719983, "max": 0.0173887597076257, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24305466318037358, "min": 0.009042761465807975, "max": 0.2443290390291105, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5214728262088886e-06, "min": 1.5214728262088886e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.282209239313333e-05, "min": 2.282209239313333e-05, "max": 0.0039690933769689005, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050712444444444, "min": 0.10050712444444444, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5076068666666667, "min": 1.3962282666666668, "max": 2.767539433333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.066173200000002e-05, "min": 6.066173200000002e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009099259800000002, "min": 0.0009099259800000002, "max": 0.13231080689000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00619171280413866, "min": 0.006113977171480656, "max": 0.5689794421195984, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09287568926811218, "min": 0.08559568226337433, "max": 3.982856035232544, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 211.73333333333332, "min": 210.13138686131387, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31760.0, "min": 15984.0, "max": 33377.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.73392078820491, "min": -1.0000000521540642, "max": 1.7871792959755866, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 258.3541974425316, "min": -30.354801654815674, "max": 259.14099791646004, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.73392078820491, "min": -1.0000000521540642, "max": 1.7871792959755866, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 258.3541974425316, "min": -30.354801654815674, "max": 259.14099791646004, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013677320852500681, "min": 0.013677320852500681, "max": 11.693298460915685, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0379208070226014, "min": 1.8333403850265313, "max": 187.09277537465096, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705560733", "python_version": "3.10.12 (main, Jan 18 2024, 15:14:31) [GCC 11.4.0]", "command_line_arguments": "/home/omar/.pyenv/versions/3.10.12/envs/rlhf/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705562784" }, "total": 2051.1559370680006, "count": 1, "self": 0.16801876400131732, "children": { "run_training.setup": { "total": 0.010624038000059954, "count": 1, "self": 0.010624038000059954 }, "TrainerController.start_learning": { "total": 2050.9772942659993, "count": 1, "self": 1.6147928751834115, "children": { "TrainerController._reset_env": { "total": 0.6259975359998862, "count": 1, "self": 0.6259975359998862 }, "TrainerController.advance": { "total": 2048.6991612388165, "count": 195036, "self": 1.4775207274569766, "children": { "env_step": { "total": 1287.8277061731478, "count": 195036, "self": 1166.8335389201993, "children": { "SubprocessEnvManager._take_step": { "total": 119.98410006001086, "count": 195036, "self": 5.1350317988071765, "children": { "TorchPolicy.evaluate": { "total": 114.84906826120368, "count": 187567, "self": 114.84906826120368 } } }, "workers": { "total": 1.0100671929376404, "count": 195036, "self": 0.0, "children": { "worker_root": { "total": 2048.7941494200104, "count": 195036, "is_parallel": true, "self": 995.055227156945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000967019000199798, "count": 1, "is_parallel": true, "self": 0.00026698600140662165, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007000329987931764, "count": 8, "is_parallel": true, "self": 0.0007000329987931764 } } }, "UnityEnvironment.step": { "total": 0.01505296899995301, "count": 1, "is_parallel": true, "self": 0.0001391280002280837, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020458800008782418, "count": 1, "is_parallel": true, "self": 0.00020458800008782418 }, "communicator.exchange": { "total": 0.01417733899961604, "count": 1, "is_parallel": true, "self": 0.01417733899961604 }, "steps_from_proto": { "total": 0.0005319140000210609, "count": 1, "is_parallel": true, "self": 0.00015708800128777511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003748259987332858, "count": 8, "is_parallel": true, "self": 0.0003748259987332858 } } } } } } }, "UnityEnvironment.step": { "total": 1053.7389222630654, "count": 195035, "is_parallel": true, "self": 20.99056299007316, "children": { "UnityEnvironment._generate_step_input": { "total": 17.357348764071503, "count": 195035, "is_parallel": true, "self": 17.357348764071503 }, "communicator.exchange": { "total": 947.2814714219066, "count": 195035, "is_parallel": true, "self": 947.2814714219066 }, "steps_from_proto": { "total": 68.10953908701413, "count": 195035, "is_parallel": true, "self": 14.092228908545621, "children": { "_process_rank_one_or_two_observation": { "total": 54.017310178468506, "count": 1560280, "is_parallel": true, "self": 54.017310178468506 } } } } } } } } } } }, "trainer_advance": { "total": 759.3939343382117, "count": 195036, "self": 3.448474896033076, "children": { "process_trajectory": { "total": 163.58176201317292, "count": 195036, "self": 163.32704501017452, "children": { "RLTrainer._checkpoint": { "total": 0.2547170029984045, "count": 6, "self": 0.2547170029984045 } } }, "_update_policy": { "total": 592.3636974290057, "count": 1398, "self": 391.9358900801535, "children": { "TorchPPOOptimizer.update": { "total": 200.42780734885218, "count": 68391, "self": 200.42780734885218 } } } } } } }, "trainer_threads": { "total": 5.800002327305265e-07, "count": 1, "self": 5.800002327305265e-07 }, "TrainerController._save_models": { "total": 0.03734203599924513, "count": 1, "self": 0.0009203109993904945, "children": { "RLTrainer._checkpoint": { "total": 0.03642172499985463, "count": 1, "self": 0.03642172499985463 } } } } } } }