{"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/reinforcement-learning-gradients-as-vitamin","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","arxiv_id":"2410.24108","date":"2024-10-31","proceeding":null,"authors":["Kai Yan","Alexander G. Schwing","Yu-Xiong Wang"],"abstract":"Decision Transformers have recently emerged as a new and compelling paradigm for offline Reinforcement Learning (RL), completing a trajectory in an autoregressive way. While improvements have been made to overcome initial shortcomings, online finetuning of decision transformers has been surprisingly under-explored. The widely adopted state-of-the-art Online Decision Transformer (ODT) still struggles when pretrained with low-reward offline data. In this paper, we theoretically analyze the online-finetuning of the decision transformer, showing that the commonly used Return-To-Go (RTG) that's far from the expected return hampers the online fine-tuning process. This problem, however, is well-addressed by the value function and advantage of standard RL algorithms. As suggested by our analysis, in our experiments, we hence find that simply adding TD3 gradients to the finetuning process of ODT effectively improves the online finetuning performance of ODT, especially if ODT is pretrained with low-reward offline data. These findings provide new directions to further improve decision transformers.","url_abs":"https://arxiv.org/abs/2410.24108v1","url_pdf":"https://arxiv.org/pdf/2410.24108v1.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":"reinforcement-learning-gradients-as-vitamin","repo_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"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":"clipped-double-q-learning","method_name":"Clipped Double Q-learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"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":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"td3","method_name":"TD3"},{"method_slug":"target-policy-smoothing","method_name":"Target Policy Smoothing"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.24108","atlas_url":"https://app.syntology.ai/?focus=2410.24108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24108"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kaiyan289/rl_as_vitamin_for_online_decision_transformers","reach":{"status":"ok"}}],"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":7,"samples":[{"code_sha256_prefix":"1c5b80da694cb240","entry":"Adanorm","repo":"kaiyan289/rl_as_vitamin_for_online_decision_transformers","repo_kind":"official","path":"critic.py","file_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers/blob/HEAD/critic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c5b80da694cb240"}},{"code_sha256_prefix":"7d29a6ab9532055c","entry":"create_dataloader","repo":"kaiyan289/rl_as_vitamin_for_online_decision_transformers","repo_kind":"official","path":"data.py","file_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d29a6ab9532055c"}},{"code_sha256_prefix":"47d4a6d45ab9c003","entry":"create_vec_eval_episodes_fn","repo":"kaiyan289/rl_as_vitamin_for_online_decision_transformers","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47d4a6d45ab9c003"}},{"code_sha256_prefix":"749edb182adc9e78","entry":"delay_reward","repo":"kaiyan289/rl_as_vitamin_for_online_decision_transformers","repo_kind":"official","path":"data.py","file_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"749edb182adc9e78"}},{"code_sha256_prefix":"f434bf3e9ec07356","entry":"discount_cumsum","repo":"kaiyan289/rl_as_vitamin_for_online_decision_transformers","repo_kind":"official","path":"data.py","file_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f434bf3e9ec07356"}},{"code_sha256_prefix":"00a33466c69c5705","entry":"load_tf_weights_in_gpt2","repo":"kaiyan289/rl_as_vitamin_for_online_decision_transformers","repo_kind":"official","path":"decision_transformer/models/trajectory_gpt2.py","file_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers/blob/HEAD/decision_transformer/models/trajectory_gpt2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00a33466c69c5705"}},{"code_sha256_prefix":"978b53b1e386dc6f","entry":"vec_evaluate_episode_rtg","repo":"kaiyan289/rl_as_vitamin_for_online_decision_transformers","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/kaiyan289/rl_as_vitamin_for_online_decision_transformers/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"978b53b1e386dc6f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}