{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47868308424949646, "min": 0.47868308424949646, "max": 1.4610393047332764, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14398.787109375, "min": 14398.787109375, "max": 44322.08984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3858831822872162, "min": -0.09690364450216293, "max": 0.49272069334983826, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 103.80257415771484, "min": -23.353778839111328, "max": 132.0491485595703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.056216731667518616, "min": 0.004240346606820822, "max": 0.41458040475845337, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.12230110168457, "min": 1.1279321908950806, "max": 98.25555419921875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06865703740775296, "min": 0.06459908171867332, "max": 0.0742594043201708, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9611985237085414, "min": 0.5198158302411956, "max": 1.062435792220925, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01439923569289801, "min": 0.0006263958559436218, "max": 0.01439923569289801, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20158929970057213, "min": 0.008143146127267084, "max": 0.20158929970057213, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.564340335728571e-06, "min": 7.564340335728571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001059007647002, "min": 0.0001059007647002, "max": 0.0033752848749050994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252141428571428, "min": 0.10252141428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352998, "min": 1.3886848, "max": 2.4250949, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026188928714285725, "min": 0.00026188928714285725, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003666450020000001, "min": 0.003666450020000001, "max": 0.11252698051000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017295876517891884, "min": 0.017295876517891884, "max": 0.5747330784797668, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24214226007461548, "min": 0.24214226007461548, "max": 4.023131370544434, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 423.5945945945946, "min": 411.041095890411, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31346.0, "min": 15984.0, "max": 32898.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4682594439065135, "min": -1.0000000521540642, "max": 1.4682594439065135, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 108.651198849082, "min": -30.385001733899117, "max": 108.651198849082, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4682594439065135, "min": -1.0000000521540642, "max": 1.4682594439065135, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 108.651198849082, "min": -30.385001733899117, "max": 108.651198849082, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07556791552240218, "min": 0.07556791552240218, "max": 11.352706035599113, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.592025748657761, "min": 5.592025748657761, "max": 181.6432965695858, "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": "1725277540", "python_version": "3.10.12 (main, Sep 2 2024, 16:47:36) [GCC 9.4.0]", "command_line_arguments": "/home/coder/.pyenv/versions/3.10.12/envs/deep-rl-unit5-3.10.12/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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725278683" }, "total": 1142.7183954680222, "count": 1, "self": 0.32335577497724444, "children": { "run_training.setup": { "total": 0.025371459021698684, "count": 1, "self": 0.025371459021698684 }, "TrainerController.start_learning": { "total": 1142.3696682340233, "count": 1, "self": 0.9652708586072549, "children": { "TrainerController._reset_env": { "total": 1.956631164997816, "count": 1, "self": 1.956631164997816 }, "TrainerController.advance": { "total": 1139.3739834093722, "count": 63465, "self": 0.8808465721085668, "children": { "env_step": { "total": 770.118118246959, "count": 63465, "self": 684.145582672325, "children": { "SubprocessEnvManager._take_step": { "total": 85.39371574629331, "count": 63465, "self": 3.4290608442388475, "children": { "TorchPolicy.evaluate": { "total": 81.96465490205446, "count": 62576, "self": 81.96465490205446 } } }, "workers": { "total": 0.5788198283407837, "count": 63465, "self": 0.0, "children": { "worker_root": { "total": 1141.0020298088202, "count": 63465, "is_parallel": true, "self": 519.9277625365066, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001257569994777441, "count": 1, "is_parallel": true, "self": 0.0003598678740672767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008977021207101643, "count": 8, "is_parallel": true, "self": 0.0008977021207101643 } } }, "UnityEnvironment.step": { "total": 0.024814944015815854, "count": 1, "is_parallel": true, "self": 0.00024273706367239356, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002369529684074223, "count": 1, "is_parallel": true, "self": 0.0002369529684074223 }, "communicator.exchange": { "total": 0.023551122983917594, "count": 1, "is_parallel": true, "self": 0.023551122983917594 }, "steps_from_proto": { "total": 0.0007841309998184443, "count": 1, "is_parallel": true, "self": 0.00018633098807185888, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005978000117465854, "count": 8, "is_parallel": true, "self": 0.0005978000117465854 } } } } } } }, "UnityEnvironment.step": { "total": 621.0742672723136, "count": 63464, "is_parallel": true, "self": 12.497521855635568, "children": { "UnityEnvironment._generate_step_input": { "total": 8.821321029216051, "count": 63464, "is_parallel": true, "self": 8.821321029216051 }, "communicator.exchange": { "total": 561.6675385510316, "count": 63464, "is_parallel": true, "self": 561.6675385510316 }, "steps_from_proto": { "total": 38.08788583643036, "count": 63464, "is_parallel": true, "self": 8.05786227126373, "children": { "_process_rank_one_or_two_observation": { "total": 30.03002356516663, "count": 507712, "is_parallel": true, "self": 30.03002356516663 } } } } } } } } } } }, "trainer_advance": { "total": 368.37501859030453, "count": 63465, "self": 1.5579841273720376, "children": { "process_trajectory": { "total": 75.66677734488621, "count": 63465, "self": 75.50434659485472, "children": { "RLTrainer._checkpoint": { "total": 0.16243075003148988, "count": 2, "self": 0.16243075003148988 } } }, "_update_policy": { "total": 291.1502571180463, "count": 445, "self": 181.79425518907374, "children": { "TorchPPOOptimizer.update": { "total": 109.35600192897255, "count": 22845, "self": 109.35600192897255 } } } } } } }, "trainer_threads": { "total": 8.880160748958588e-07, "count": 1, "self": 8.880160748958588e-07 }, "TrainerController._save_models": { "total": 0.07378191302996129, "count": 1, "self": 0.00463525700615719, "children": { "RLTrainer._checkpoint": { "total": 0.0691466560238041, "count": 1, "self": 0.0691466560238041 } } } } } } }