{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41191014647483826, "min": 0.410511314868927, "max": 1.3573895692825317, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12265.0361328125, "min": 12265.0361328125, "max": 41177.76953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5855107307434082, "min": -0.13582341372966766, "max": 0.5885475277900696, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 165.6995391845703, "min": -32.190147399902344, "max": 165.6995391845703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025272591039538383, "min": -0.04805679991841316, "max": 0.591279149055481, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.1521430015563965, "min": -13.455904006958008, "max": 140.13316345214844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06838421758757683, "min": 0.06552355552202414, "max": 0.0722737830309518, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9573790462260756, "min": 0.4899935327308391, "max": 1.0631852610180537, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014576204605483714, "min": 0.00026563125680687454, "max": 0.01567977282969628, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.204066864476772, "min": 0.0031875750816824943, "max": 0.2195168196157479, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.648468879114282e-06, "min": 7.648468879114282e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010707856430759995, "min": 0.00010707856430759995, "max": 0.0034370688543104, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254945714285714, "min": 0.10254945714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356924, "min": 1.3886848, "max": 2.401491, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002646907685714285, "min": 0.0002646907685714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003705670759999999, "min": 0.003705670759999999, "max": 0.11457439104000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01213882863521576, "min": 0.01213882863521576, "max": 0.580790638923645, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16994360089302063, "min": 0.16994360089302063, "max": 4.065534591674805, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.4719101123595, "min": 317.7608695652174, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28967.0, "min": 15984.0, "max": 33343.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6070943621269773, "min": -1.0000000521540642, "max": 1.6387434588826222, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 143.03139822930098, "min": -31.99480164051056, "max": 150.76439821720123, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6070943621269773, "min": -1.0000000521540642, "max": 1.6387434588826222, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 143.03139822930098, "min": -31.99480164051056, "max": 150.76439821720123, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0409522373327368, "min": 0.0407138881722779, "max": 12.354949859902263, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6447491226135753, "min": 3.6447491226135753, "max": 197.6791977584362, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704451162", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704453326" }, "total": 2164.176653004, "count": 1, "self": 0.5393733010000687, "children": { "run_training.setup": { "total": 0.045887376000109725, "count": 1, "self": 0.045887376000109725 }, "TrainerController.start_learning": { "total": 2163.591392327, "count": 1, "self": 1.3315497310168212, "children": { "TrainerController._reset_env": { "total": 2.3400908260000506, "count": 1, "self": 2.3400908260000506 }, "TrainerController.advance": { "total": 2159.8362210999826, "count": 63788, "self": 1.441102931968544, "children": { "env_step": { "total": 1551.81913347799, "count": 63788, "self": 1423.2697383639943, "children": { "SubprocessEnvManager._take_step": { "total": 127.71271043499405, "count": 63788, "self": 4.685208758019826, "children": { "TorchPolicy.evaluate": { "total": 123.02750167697423, "count": 62553, "self": 123.02750167697423 } } }, "workers": { "total": 0.8366846790015643, "count": 63788, "self": 0.0, "children": { "worker_root": { "total": 2158.9348992080454, "count": 63788, "is_parallel": true, "self": 852.5070708969806, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018489200001567951, "count": 1, "is_parallel": true, "self": 0.0006173270003273501, "children": { "_process_rank_one_or_two_observation": { "total": 0.001231592999829445, "count": 8, "is_parallel": true, "self": 0.001231592999829445 } } }, "UnityEnvironment.step": { "total": 0.07042400599993925, "count": 1, "is_parallel": true, "self": 0.0006043890000455576, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004804279999461869, "count": 1, "is_parallel": true, "self": 0.0004804279999461869 }, "communicator.exchange": { "total": 0.06759693399999378, "count": 1, "is_parallel": true, "self": 0.06759693399999378 }, "steps_from_proto": { "total": 0.0017422549999537296, "count": 1, "is_parallel": true, "self": 0.0003649279994988319, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013773270004548976, "count": 8, "is_parallel": true, "self": 0.0013773270004548976 } } } } } } }, "UnityEnvironment.step": { "total": 1306.4278283110648, "count": 63787, "is_parallel": true, "self": 34.751958534882306, "children": { "UnityEnvironment._generate_step_input": { "total": 26.196808810059565, "count": 63787, "is_parallel": true, "self": 26.196808810059565 }, "communicator.exchange": { "total": 1144.524449313097, "count": 63787, "is_parallel": true, "self": 1144.524449313097 }, "steps_from_proto": { "total": 100.95461165302595, "count": 63787, "is_parallel": true, "self": 20.364912821812368, "children": { "_process_rank_one_or_two_observation": { "total": 80.58969883121358, "count": 510296, "is_parallel": true, "self": 80.58969883121358 } } } } } } } } } } }, "trainer_advance": { "total": 606.5759846900244, "count": 63788, "self": 2.575056207084117, "children": { "process_trajectory": { "total": 123.75336418394204, "count": 63788, "self": 123.56403019394224, "children": { "RLTrainer._checkpoint": { "total": 0.18933398999979545, "count": 2, "self": 0.18933398999979545 } } }, "_update_policy": { "total": 480.2475642989982, "count": 451, "self": 281.9987276679815, "children": { "TorchPPOOptimizer.update": { "total": 198.24883663101673, "count": 22827, "self": 198.24883663101673 } } } } } } }, "trainer_threads": { "total": 2.9900002118665725e-06, "count": 1, "self": 2.9900002118665725e-06 }, "TrainerController._save_models": { "total": 0.08352768000031574, "count": 1, "self": 0.001408433000506193, "children": { "RLTrainer._checkpoint": { "total": 0.08211924699980955, "count": 1, "self": 0.08211924699980955 } } } } } } }