{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-large-recurrent-action-model-xlstm-enables","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","arxiv_id":"2410.22391","date":"2024-10-29","proceeding":null,"authors":["Thomas Schmied","Thomas Adler","Vihang Patil","Maximilian Beck","Korbinian Pöppel","Johannes Brandstetter","Günter Klambauer","Razvan Pascanu","Sepp Hochreiter"],"abstract":"In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Existing models are primarily based on the Transformer architecture, which result in powerful agents. However, due to slow inference times, Transformer-based approaches are impractical for real-time applications, such as robotics. Recently, modern recurrent architectures, such as xLSTM and Mamba, have been proposed that exhibit parallelization benefits during training similar to the Transformer architecture while offering fast inference. In this work, we study the aptitude of these modern recurrent architectures for large action models. Consequently, we propose a Large Recurrent Action Model (LRAM) with an xLSTM at its core that comes with linear-time inference complexity and natural sequence length extrapolation abilities. Experiments on 432 tasks from 6 domains show that LRAM compares favorably to Transformers in terms of performance and speed.","url_abs":"https://arxiv.org/abs/2410.22391v1","url_pdf":"https://arxiv.org/pdf/2410.22391v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-large-recurrent-action-model-xlstm-enables","repo_url":"https://github.com/ml-jku/lram","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mamba","method_name":"Mamba"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.22391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22391"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ml-jku/lram","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"47f553906dc6d889","entry":"discount_cumsum","repo":"ml-jku/lram","repo_kind":"official","path":"src/buffers/buffer_utils.py","file_url":"https://github.com/ml-jku/lram/blob/HEAD/src/buffers/buffer_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47f553906dc6d889"}},{"code_sha256_prefix":"561155d921a7e0b3","entry":"discount_cumsum_np","repo":"ml-jku/lram","repo_kind":"official","path":"src/buffers/buffer_utils.py","file_url":"https://github.com/ml-jku/lram/blob/HEAD/src/buffers/buffer_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"561155d921a7e0b3"}},{"code_sha256_prefix":"bd2bb148a44d0eb1","entry":"discount_cumsum_torch","repo":"ml-jku/lram","repo_kind":"official","path":"src/buffers/buffer_utils.py","file_url":"https://github.com/ml-jku/lram/blob/HEAD/src/buffers/buffer_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd2bb148a44d0eb1"}},{"code_sha256_prefix":"09f86a57b3ec134a","entry":"dropout_dims","repo":"ml-jku/lram","repo_kind":"official","path":"src/algos/agent_utils.py","file_url":"https://github.com/ml-jku/lram/blob/HEAD/src/algos/agent_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09f86a57b3ec134a"}},{"code_sha256_prefix":"8357e0d1e97197da","entry":"make_augmentations","repo":"ml-jku/lram","repo_kind":"official","path":"src/augmentations/augs.py","file_url":"https://github.com/ml-jku/lram/blob/HEAD/src/augmentations/augs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8357e0d1e97197da"}},{"code_sha256_prefix":"4c1536617de4bc00","entry":"make_gaussian_noise","repo":"ml-jku/lram","repo_kind":"official","path":"src/algos/agent_utils.py","file_url":"https://github.com/ml-jku/lram/blob/HEAD/src/algos/agent_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c1536617de4bc00"}},{"code_sha256_prefix":"44caa4c4f26ad0bf","entry":"make_random_proj_matrix","repo":"ml-jku/lram","repo_kind":"official","path":"src/algos/agent_utils.py","file_url":"https://github.com/ml-jku/lram/blob/HEAD/src/algos/agent_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44caa4c4f26ad0bf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}