{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8176532983779907, "min": 0.8135545253753662, "max": 1.382722020149231, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 24595.01171875, "min": 24588.87109375, "max": 41946.25390625, "count": 16 }, "Pyramids.Step.mean": { "value": 479943.0, "min": 29895.0, "max": 479943.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479943.0, "min": 29895.0, "max": 479943.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07309549301862717, "min": -0.15802617371082306, "max": -0.07309549301862717, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.689109802246094, "min": -37.45220184326172, "max": -17.689109802246094, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021365126594901085, "min": 0.021365126594901085, "max": 0.32575222849845886, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.170360565185547, "min": 5.170360565185547, "max": 77.20327758789062, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06746886548353359, "min": 0.0651850253043249, "max": 0.07238381012501996, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9445641167694703, "min": 0.5790704810001597, "max": 0.9868998093397721, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0017575926825602868, "min": 0.00011927292466538447, "max": 0.0054866066686830575, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.024606297555844016, "min": 0.0016698209453153826, "max": 0.04389285334946446, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0896550177371422e-05, "min": 2.0896550177371422e-05, "max": 0.0002900043033318999, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002925517024831999, "min": 0.0002925517024831999, "max": 0.0030633001789, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10696548571428573, "min": 0.10696548571428573, "max": 0.19666810000000004, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4975168, "min": 1.4975168, "max": 2.3385204, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007058520228571429, "min": 0.0007058520228571429, "max": 0.009667143189999998, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.00988192832, "min": 0.00988192832, "max": 0.10212789000000001, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02365005947649479, "min": 0.02365005947649479, "max": 0.4620400369167328, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.33110082149505615, "min": 0.33110082149505615, "max": 3.6963202953338623, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 948.0625, "min": 891.9117647058823, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30338.0, "min": 16182.0, "max": 32689.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.6986563000828028, "min": -0.9998250515200198, "max": -0.5863818650444349, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -22.35700160264969, "min": -31.994401648640633, "max": -14.198000892996788, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.6986563000828028, "min": -0.9998250515200198, "max": -0.5863818650444349, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -22.35700160264969, "min": -31.994401648640633, "max": -14.198000892996788, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.23769681376870722, "min": 0.23769681376870722, "max": 8.59420027277049, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 7.606298040598631, "min": 7.60329354275018, "max": 146.1014046370983, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727018478", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727019579" }, "total": 1100.8744032769996, "count": 1, "self": 0.49196001199925377, "children": { "run_training.setup": { "total": 0.05111479200013491, "count": 1, "self": 0.05111479200013491 }, "TrainerController.start_learning": { "total": 1100.3313284730002, "count": 1, "self": 0.7901767760035909, "children": { "TrainerController._reset_env": { "total": 1.86582231400007, "count": 1, "self": 1.86582231400007 }, "TrainerController.advance": { "total": 1097.5916777349971, "count": 31504, "self": 0.7954811078425337, "children": { "env_step": { "total": 746.0315293459989, "count": 31504, "self": 661.8866792970043, "children": { "SubprocessEnvManager._take_step": { "total": 83.67506468306192, "count": 31504, "self": 2.4741520921456868, "children": { "TorchPolicy.evaluate": { "total": 81.20091259091623, "count": 31325, "self": 81.20091259091623 } } }, "workers": { "total": 0.4697853659326938, "count": 31504, "self": 0.0, "children": { "worker_root": { "total": 1097.4903674151005, "count": 31504, "is_parallel": true, "self": 501.027891339234, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002110872999764979, "count": 1, "is_parallel": true, "self": 0.0007216560002234473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013892169995415315, "count": 8, "is_parallel": true, "self": 0.0013892169995415315 } } }, "UnityEnvironment.step": { "total": 0.05379685700017944, "count": 1, "is_parallel": true, "self": 0.000627139999778592, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004914720002489048, "count": 1, "is_parallel": true, "self": 0.0004914720002489048 }, "communicator.exchange": { "total": 0.05106431200010775, "count": 1, "is_parallel": true, "self": 0.05106431200010775 }, "steps_from_proto": { "total": 0.0016139330000441987, "count": 1, "is_parallel": true, "self": 0.000342248999459116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012716840005850827, "count": 8, "is_parallel": true, "self": 0.0012716840005850827 } } } } } } }, "UnityEnvironment.step": { "total": 596.4624760758666, "count": 31503, "is_parallel": true, "self": 17.833133531761632, "children": { "UnityEnvironment._generate_step_input": { "total": 11.539959795043615, "count": 31503, "is_parallel": true, "self": 11.539959795043615 }, "communicator.exchange": { "total": 517.2011844289996, "count": 31503, "is_parallel": true, "self": 517.2011844289996 }, "steps_from_proto": { "total": 49.88819832006175, "count": 31503, "is_parallel": true, "self": 10.622825373837713, "children": { "_process_rank_one_or_two_observation": { "total": 39.26537294622403, "count": 252024, "is_parallel": true, "self": 39.26537294622403 } } } } } } } } } } }, "trainer_advance": { "total": 350.76466728115565, "count": 31504, "self": 1.3830388731457788, "children": { "process_trajectory": { "total": 65.9889750240136, "count": 31504, "self": 65.87879715501276, "children": { "RLTrainer._checkpoint": { "total": 0.11017786900083593, "count": 1, "self": 0.11017786900083593 } } }, "_update_policy": { "total": 283.3926533839963, "count": 213, "self": 160.46562924104273, "children": { "TorchPPOOptimizer.update": { "total": 122.92702414295354, "count": 11364, "self": 122.92702414295354 } } } } } } }, "trainer_threads": { "total": 9.189998309011571e-07, "count": 1, "self": 9.189998309011571e-07 }, "TrainerController._save_models": { "total": 0.08365072899960069, "count": 1, "self": 0.0013260079995234264, "children": { "RLTrainer._checkpoint": { "total": 0.08232472100007726, "count": 1, "self": 0.08232472100007726 } } } } } } }