{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9911152124404907, "min": 0.8980339765548706, "max": 1.4047480821609497, "count": 5 }, "Pyramids.Policy.Entropy.sum": { "value": 30018.8984375, "min": 26897.9140625, "max": 42614.4375, "count": 5 }, "Pyramids.Step.mean": { "value": 149944.0, "min": 29952.0, "max": 149944.0, "count": 5 }, "Pyramids.Step.sum": { "value": 149944.0, "min": 29952.0, "max": 149944.0, "count": 5 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07995567470788956, "min": -0.09970849752426147, "max": 0.06552807241678238, "count": 5 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.189361572265625, "min": -24.12945556640625, "max": 15.530152320861816, "count": 5 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07301373034715652, "min": 0.07301373034715652, "max": 0.4235268831253052, "count": 5 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 17.52329444885254, "min": 17.52329444885254, "max": 100.37586975097656, "count": 5 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06972431661052644, "min": 0.06972431661052644, "max": 0.07294068138432408, "count": 5 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9761404325473702, "min": 0.49341854054999973, "max": 0.9761404325473702, "count": 5 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0008532991761625281, "min": 0.0008532991761625281, "max": 0.011349813299919435, "count": 5 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.011946188466275393, "min": 0.011946188466275393, "max": 0.07944869309943604, "count": 5 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00028652453306325236, "min": 0.00028652453306325236, "max": 0.00029838354339596195, "count": 5 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.004011343462885533, "min": 0.0020886848037717336, "max": 0.004011343462885533, "count": 5 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1955081761904762, "min": 0.1955081761904762, "max": 0.19946118095238097, "count": 5 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.7371144666666667, "min": 1.3962282666666668, "max": 2.7371144666666667, "count": 5 }, "Pyramids.Policy.Beta.mean": { "value": 0.009551266801428574, "min": 0.009551266801428574, "max": 0.009946171977142856, "count": 5 }, "Pyramids.Policy.Beta.sum": { "value": 0.13371773522000002, "min": 0.06962320384, "max": 0.13371773522000002, "count": 5 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.05838913843035698, "min": 0.05838913843035698, "max": 0.5061315298080444, "count": 5 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.8174479603767395, "min": 0.8174479603767395, "max": 3.5429208278656006, "count": 5 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 991.0645161290323, "min": 928.1212121212121, "max": 999.0, "count": 5 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30723.0, "min": 15984.0, "max": 32576.0, "count": 5 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9295938017312437, "min": -1.0000000521540642, "max": -0.5788545929121248, "count": 5 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -29.7470016553998, "min": -29.7470016553998, "max": -16.000000834465027, "count": 5 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9295938017312437, "min": -1.0000000521540642, "max": -0.5788545929121248, "count": 5 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -29.7470016553998, "min": -29.7470016553998, "max": -16.000000834465027, "count": 5 }, "Pyramids.Policy.RndReward.mean": { "value": 0.6363741207169369, "min": 0.6363741207169369, "max": 10.990128256380558, "count": 5 }, "Pyramids.Policy.RndReward.sum": { "value": 20.36397186294198, "min": 20.36397186294198, "max": 175.84205210208893, "count": 5 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702203732", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702204054" }, "total": 321.43847693199996, "count": 1, "self": 0.4829570669999157, "children": { "run_training.setup": { "total": 0.05337012000018149, "count": 1, "self": 0.05337012000018149 }, "TrainerController.start_learning": { "total": 320.90214974499986, "count": 1, "self": 0.22451296099825413, "children": { "TrainerController._reset_env": { "total": 3.069118000999879, "count": 1, "self": 3.069118000999879 }, "TrainerController.advance": { "total": 317.60807606400203, "count": 9968, "self": 0.2271747299805611, "children": { "env_step": { "total": 214.05444037002826, "count": 9968, "self": 191.3387859379859, "children": { "SubprocessEnvManager._take_step": { "total": 22.576152342012847, "count": 9968, "self": 0.7616145310212232, "children": { "TorchPolicy.evaluate": { "total": 21.814537810991624, "count": 9938, "self": 21.814537810991624 } } }, "workers": { "total": 0.13950209002950942, "count": 9968, "self": 0.0, "children": { "worker_root": { "total": 320.1145002039766, "count": 9968, "is_parallel": true, "self": 147.52326967897125, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019091890003437584, "count": 1, "is_parallel": true, "self": 0.0006341910011542495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012749979991895088, "count": 8, "is_parallel": true, "self": 0.0012749979991895088 } } }, "UnityEnvironment.step": { "total": 0.04897270399987974, "count": 1, "is_parallel": true, "self": 0.0005905289999645902, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005321259995980654, "count": 1, "is_parallel": true, "self": 0.0005321259995980654 }, "communicator.exchange": { "total": 0.04608234600027572, "count": 1, "is_parallel": true, "self": 0.04608234600027572 }, "steps_from_proto": { "total": 0.0017677030000413652, "count": 1, "is_parallel": true, "self": 0.0003437610002947622, "children": { "_process_rank_one_or_two_observation": { "total": 0.001423941999746603, "count": 8, "is_parallel": true, "self": 0.001423941999746603 } } } } } } }, "UnityEnvironment.step": { "total": 172.59123052500536, "count": 9967, "is_parallel": true, "self": 5.494523721024962, "children": { "UnityEnvironment._generate_step_input": { "total": 3.794012789977387, "count": 9967, "is_parallel": true, "self": 3.794012789977387 }, "communicator.exchange": { "total": 147.8359004930171, "count": 9967, "is_parallel": true, "self": 147.8359004930171 }, "steps_from_proto": { "total": 15.466793520985902, "count": 9967, "is_parallel": true, "self": 3.1044886189342833, "children": { "_process_rank_one_or_two_observation": { "total": 12.36230490205162, "count": 79736, "is_parallel": true, "self": 12.36230490205162 } } } } } } } } } } }, "trainer_advance": { "total": 103.32646096399321, "count": 9968, "self": 0.3257165049553805, "children": { "process_trajectory": { "total": 19.328702731040266, "count": 9968, "self": 19.328702731040266 }, "_update_policy": { "total": 83.67204172799757, "count": 59, "self": 50.175405558982675, "children": { "TorchPPOOptimizer.update": { "total": 33.49663616901489, "count": 3616, "self": 33.49663616901489 } } } } } } }, "trainer_threads": { "total": 1.3029998626734596e-06, "count": 1, "self": 1.3029998626734596e-06 }, "TrainerController._save_models": { "total": 0.00044141599983049673, "count": 1, "self": 2.7102999865746824e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0004143129999647499, "count": 1, "self": 0.0004143129999647499 } } } } } } }