Papers › Think Before You Act: Decision Transformers with Working Memory

Think Before You Act: Decision Transformers with Working Memory

24 May 2023arXiv:2305.16338archive 2025-07-28

Jikun Kang, Romain Laroche, Xingdi Yuan, Adam Trischler, Xue Liu, Jie Fu

Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. As a result, training on a new task may deteriorate the model's performance on previous tasks. In contrast to LLMs' implicit memory mechanism, the human brain utilizes distributed memory storage, which helps manage and organize multiple skills efficiently, mitigating the forgetting phenomenon. Inspired by this, we propose a working memory module to store, blend, and retrieve information for different downstream tasks. Evaluation results show that the proposed method improves training efficiency and generalization in Atari games and Meta-World object manipulation tasks. Moreover, we demonstrate that memory fine-tuning further enhances the adaptability of the proposed architecture.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.16338")

Code

Syntology Ran 7 of 12 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

luciferkonn/dt_mem officialmentioned in papermentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 7 ran; 2 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
1ran · fixture could not drive it
3ran
5unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from luciferkonn/dt_mem. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

GroupLinearLayer luciferkonn/dt_mem/src/model.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 161899026ce0eb8d · report
RelationalMemory luciferkonn/dt_mem/src/model.py official repository ran MIT (permissive) · 83fc917b52b947b3 · report
RepeatLinear luciferkonn/dt_mem/src/model.py official repository ran MIT (permissive) · a0c499b6fb911e20 · report
accuracy luciferkonn/dt_mem/src/model.py official repository ran · honoured contract fingerprinted MIT (permissive) · 85999f9cb6163ec0 · report
cross_entropy luciferkonn/dt_mem/src/model.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 7a16e89219207505 · report
encode_return luciferkonn/dt_mem/src/model.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · c77c68839b869e29 · report
encode_reward luciferkonn/dt_mem/src/model.py official repository ran · honoured contract fingerprinted MIT (permissive) · dd64b6c6ba18470c · report
CausalSelfAttention luciferkonn/dt_mem/src/model.py official repository unverified MIT (permissive) · c59ed427653b94b7 · report
DecisionTransformer luciferkonn/dt_mem/src/model.py official repository unverified MIT (permissive) · 23804b0d6173123a · report
DenseBlock luciferkonn/dt_mem/src/model.py official repository unverified MIT (permissive) · 88fdc33643df68a8 · report
GPT2 luciferkonn/dt_mem/src/model.py official repository unverified MIT (permissive) · 331bf757c4894bec · report
count_parameters luciferkonn/dt_mem/src/model.py official repository unverified MIT (permissive) · 75bf37896d765771 · report

Tasks

Atari GamesDecision MakingLanguage ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections