{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15532980859279633, "min": 0.15532980859279633, "max": 0.17766109108924866, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 4612.673828125, "min": 4612.673828125, "max": 5406.58251953125, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 233.28125, "min": 217.61068702290078, "max": 243.5546218487395, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29860.0, "min": 28507.0, "max": 29860.0, "count": 3 }, "Pyramids.Step.mean": { "value": 3089950.0, "min": 3029937.0, "max": 3089950.0, "count": 3 }, "Pyramids.Step.sum": { "value": 3089950.0, "min": 3029937.0, "max": 3089950.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8099780082702637, "min": 0.7502532601356506, "max": 0.8099780082702637, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 243.80337524414062, "min": 223.57546997070312, "max": 243.80337524414062, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015061672776937485, "min": 0.010099782608449459, "max": 0.015061672776937485, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.533563613891602, "min": 2.9895355701446533, "max": 4.533563613891602, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7667187365004793, "min": 1.7563643955578239, "max": 1.7671090739242958, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 226.13999827206135, "min": 207.2509986758232, "max": 233.25839775800705, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7667187365004793, "min": 1.7563643955578239, "max": 1.7671090739242958, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 226.13999827206135, "min": 207.2509986758232, "max": 233.25839775800705, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015147481277267616, "min": 0.014441218573527734, "max": 0.015482416476608427, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9388776034902548, "min": 1.8269251442397945, "max": 1.9388776034902548, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06723150747296003, "min": 0.06723150747296003, "max": 0.06923204550236864, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9412411046214404, "min": 0.9412411046214404, "max": 0.9692486370331609, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01443189695557868, "min": 0.013293105223315898, "max": 0.015231430484813504, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2020465573781015, "min": 0.18610347312642259, "max": 0.21324002678738907, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.2189471215552982e-06, "min": 3.2189471215552982e-06, "max": 1.0862917560792624e-05, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.5065259701774174e-05, "min": 4.5065259701774174e-05, "max": 0.00015208084585109673, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10080471198156683, "min": 0.10080471198156683, "max": 0.10271570506912443, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4112659677419357, "min": 1.4112659677419357, "max": 1.438019870967742, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 9.03907269585253e-05, "min": 9.03907269585253e-05, "max": 0.0002812989364055299, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0012654701774193543, "min": 0.0012654701774193543, "max": 0.0039381851096774185, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006127002649009228, "min": 0.006127002649009228, "max": 0.006317739374935627, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08577803522348404, "min": 0.08577803522348404, "max": 0.08844835311174393, "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": "1674275685", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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 --resume", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674275923" }, "total": 237.75779606200012, "count": 1, "self": 0.4262424729986378, "children": { "run_training.setup": { "total": 0.10669388600035745, "count": 1, "self": 0.10669388600035745 }, "TrainerController.start_learning": { "total": 237.22485970300113, "count": 1, "self": 0.1224114399519749, "children": { "TrainerController._reset_env": { "total": 5.950634958999217, "count": 1, "self": 5.950634958999217 }, "TrainerController.advance": { "total": 231.05234738405125, "count": 6634, "self": 0.11989232798623561, "children": { "env_step": { "total": 167.02867412602427, "count": 6634, "self": 157.20707423208842, "children": { "SubprocessEnvManager._take_step": { "total": 9.749658120961612, "count": 6634, "self": 0.4155832759097393, "children": { "TorchPolicy.evaluate": { "total": 9.334074845051873, "count": 6306, "self": 3.1898450220560335, "children": { "TorchPolicy.sample_actions": { "total": 6.14422982299584, "count": 6306, "self": 6.14422982299584 } } } } }, "workers": { "total": 0.07194177297424176, "count": 6634, "self": 0.0, "children": { "worker_root": { "total": 236.73982923492258, "count": 6634, "is_parallel": true, "self": 88.89418111704981, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017270869993808446, "count": 1, "is_parallel": true, "self": 0.0006711359965265729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010559510028542718, "count": 8, "is_parallel": true, "self": 0.0010559510028542718 } } }, "UnityEnvironment.step": { "total": 0.04386864499974763, "count": 1, "is_parallel": true, "self": 0.0004536559990810929, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040729700049269013, "count": 1, "is_parallel": true, "self": 0.00040729700049269013 }, "communicator.exchange": { "total": 0.04152122899904498, "count": 1, "is_parallel": true, "self": 0.04152122899904498 }, "steps_from_proto": { "total": 0.0014864630011288682, "count": 1, "is_parallel": true, "self": 0.00037607699778163806, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011103860033472301, "count": 8, "is_parallel": true, "self": 0.0011103860033472301 } } } } } } }, "UnityEnvironment.step": { "total": 147.84564811787277, "count": 6633, "is_parallel": true, "self": 2.6657022408817284, "children": { "UnityEnvironment._generate_step_input": { "total": 2.100817538017509, "count": 6633, "is_parallel": true, "self": 2.100817538017509 }, "communicator.exchange": { "total": 133.57384340699718, "count": 6633, "is_parallel": true, "self": 133.57384340699718 }, "steps_from_proto": { "total": 9.505284931976348, "count": 6633, "is_parallel": true, "self": 2.137392321099469, "children": { "_process_rank_one_or_two_observation": { "total": 7.367892610876879, "count": 53064, "is_parallel": true, "self": 7.367892610876879 } } } } } } } } } } }, "trainer_advance": { "total": 63.90378093004074, "count": 6634, "self": 0.23311644107161555, "children": { "process_trajectory": { "total": 14.775357912974869, "count": 6634, "self": 14.775357912974869 }, "_update_policy": { "total": 48.895306575994255, "count": 47, "self": 18.456487726994965, "children": { "TorchPPOOptimizer.update": { "total": 30.43881884899929, "count": 2256, "self": 30.43881884899929 } } } } } } }, "trainer_threads": { "total": 1.0809999366756529e-06, "count": 1, "self": 1.0809999366756529e-06 }, "TrainerController._save_models": { "total": 0.09946483899875602, "count": 1, "self": 0.001780042997779674, "children": { "RLTrainer._checkpoint": { "total": 0.09768479600097635, "count": 1, "self": 0.09768479600097635 } } } } } } }