{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40878114104270935, "min": 0.40878114104270935, "max": 1.4681951999664307, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12276.515625, "min": 12276.515625, "max": 44539.16796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989964.0, "min": 29952.0, "max": 989964.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989964.0, "min": 29952.0, "max": 989964.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4345107078552246, "min": -0.11549055576324463, "max": 0.5166305303573608, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.88337707519531, "min": -27.833223342895508, "max": 141.04013061523438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.36848998069763184, "min": -0.36848998069763184, "max": 0.3253829777240753, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -99.1238021850586, "min": -99.1238021850586, "max": 78.09191131591797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06726208474230758, "min": 0.06538947978082837, "max": 0.07321019653376759, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.941669186392306, "min": 0.4852712989096321, "max": 1.0563431158467818, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.03273473415704423, "min": 8.286556583453304e-05, "max": 0.03273473415704423, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.4582862781986193, "min": 0.0010772523558489294, "max": 0.4582862781986193, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.327661843192859e-06, "min": 7.327661843192859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010258726580470003, "min": 0.00010258726580470003, "max": 0.0029526781157739996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244252142857145, "min": 0.10244252142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341953000000003, "min": 1.3691136000000002, "max": 2.3167245000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002540078907142858, "min": 0.0002540078907142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003556110470000001, "min": 0.003556110470000001, "max": 0.09843417739999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012379638850688934, "min": 0.012379638850688934, "max": 0.5159215331077576, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17331494390964508, "min": 0.17331494390964508, "max": 3.6114509105682373, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 405.1, "min": 375.26582278481015, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28357.0, "min": 15984.0, "max": 32163.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4519914126821927, "min": -1.0000000521540642, "max": 1.530898614799323, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 101.63939888775349, "min": -32.000001668930054, "max": 114.34959848970175, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4519914126821927, "min": -1.0000000521540642, "max": 1.530898614799323, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 101.63939888775349, "min": -32.000001668930054, "max": 114.34959848970175, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05196117063626714, "min": 0.05113220304291978, "max": 10.417551893740892, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6372819445386995, "min": 3.6372819445386995, "max": 166.68083029985428, "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": "1779944826", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/home/flandre/Desktop/huggingface_deep_rl/hf_rl_unit5/.venv/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", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1779945326" }, "total": 499.56567917899883, "count": 1, "self": 0.16644103999715298, "children": { "run_training.setup": { "total": 0.009126566001214087, "count": 1, "self": 0.009126566001214087 }, "TrainerController.start_learning": { "total": 499.39011157300047, "count": 1, "self": 0.47579284982566605, "children": { "TrainerController._reset_env": { "total": 0.909893459000159, "count": 1, "self": 0.909893459000159 }, "TrainerController.advance": { "total": 497.98398048517447, "count": 63507, "self": 0.431732440372798, "children": { "env_step": { "total": 300.5454312757356, "count": 63507, "self": 255.48152451703208, "children": { "SubprocessEnvManager._take_step": { "total": 44.759416355967915, "count": 63507, "self": 1.531310798969571, "children": { "TorchPolicy.evaluate": { "total": 43.228105556998344, "count": 62565, "self": 43.228105556998344 } } }, "workers": { "total": 0.3044904027356097, "count": 63507, "self": 0.0, "children": { "worker_root": { "total": 498.7475951610231, "count": 63507, "is_parallel": true, "self": 272.93192726416964, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0005540490001294529, "count": 1, "is_parallel": true, "self": 0.00016665899784129579, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003873900022881571, "count": 8, "is_parallel": true, "self": 0.0003873900022881571 } } }, "UnityEnvironment.step": { "total": 0.013446479999402072, "count": 1, "is_parallel": true, "self": 0.00013298999874677975, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00013822000073560048, "count": 1, "is_parallel": true, "self": 0.00013822000073560048 }, "communicator.exchange": { "total": 0.01283051000064006, "count": 1, "is_parallel": true, "self": 0.01283051000064006 }, "steps_from_proto": { "total": 0.0003447599992796313, "count": 1, "is_parallel": true, "self": 9.61599980655592e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0002486000012140721, "count": 8, "is_parallel": true, "self": 0.0002486000012140721 } } } } } } }, "UnityEnvironment.step": { "total": 225.81566789685348, "count": 63506, "is_parallel": true, "self": 6.762632917118026, "children": { "UnityEnvironment._generate_step_input": { "total": 4.29348586789456, "count": 63506, "is_parallel": true, "self": 4.29348586789456 }, "communicator.exchange": { "total": 197.58677681969675, "count": 63506, "is_parallel": true, "self": 197.58677681969675 }, "steps_from_proto": { "total": 17.172772292144145, "count": 63506, "is_parallel": true, "self": 4.016796649675598, "children": { "_process_rank_one_or_two_observation": { "total": 13.155975642468547, "count": 508048, "is_parallel": true, "self": 13.155975642468547 } } } } } } } } } } }, "trainer_advance": { "total": 197.00681676906606, "count": 63507, "self": 0.8099450961781258, "children": { "process_trajectory": { "total": 41.97835010486597, "count": 63507, "self": 41.92500897586615, "children": { "RLTrainer._checkpoint": { "total": 0.053341128999818466, "count": 2, "self": 0.053341128999818466 } } }, "_update_policy": { "total": 154.21852156802197, "count": 433, "self": 90.83175494714851, "children": { "TorchPPOOptimizer.update": { "total": 63.38676662087346, "count": 22851, "self": 63.38676662087346 } } } } } } }, "trainer_threads": { "total": 4.3000000005122274e-07, "count": 1, "self": 4.3000000005122274e-07 }, "TrainerController._save_models": { "total": 0.020444349000172224, "count": 1, "self": 0.0002710090011532884, "children": { "RLTrainer._checkpoint": { "total": 0.020173339999018935, "count": 1, "self": 0.020173339999018935 } } } } } } }