The paper presents a complete enumeration of all possible representations and binary action rules in a uniform four‑state world, comparing their retained information, payoff (task accuracy), and cost under various tariffs. It shows that a representation with less retained information can sometimes yield higher payoff, while in other cases the more informative representation performs better, and that equal payoff can occur with different information amounts. The study demonstrates how the specific distinctions preserved by a representation, the choice of action rule, and the cost assumptions jointly determine performance, offering a reproducible model for exploring these trade‑offs.
By Aleksandr M. Shtraukh-Adamsky, Vladimir M. Adamsky, Irina G. Voloshina, Artemiy D. Spitsyn
arXiv:2610.20004v1 Announce Type: new
Abstract: Transformers can perform in-context reinforcement learning without parameter updates. However, existing theoretical constructions often require context...
By Yajie Zhao, Yingjun Mo, Zhiyong Wang, Bo Tang, Chao Xu, Fang Kong
arXiv:2610.08884v1 Announce Type: cross
Abstract: A declared task can sometimes certify a reduced source before a downstream encoder, codebook, rate, distortion target, or optimizer is chosen. This p...
By Joss Armstrong
arXiv:2608. 05085v1 Announce Type: cross Abstract: Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop.
By Ahmed Hassoon, Mark Dredze
Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a fundamental constraint: language is a compressed and capacity-limited interface for conveying task information.
arXiv:2606. 11171v2 Announce Type: replace Abstract: We develop indexed Bellman information complexity, a representation-level theory of interactive decision making centered on information indices and reference histories.
By Yunbei Xu
arXiv:2609.21523v1 Announce Type: new
Abstract: A system may be compressed before its downstream task is fully known. We ask how much retained state is then necessary and how much can be saved by lim...
By Ronald Katende
arXiv:2601. 22496v2 Announce Type: replace-cross Abstract: In offline goal-conditioned reinforcement learning (GCRL), hierarchical approaches decompose long-horizon tasks into high-level subgoal prediction and low-level action execution.
By Jinu Hyeon, Woobin Park, Hongjoon Ahn, Taesup Moon
arXiv:2609. 21523v2 Announce Type: replace Abstract: A state may need to be compressed before its exact downstream task is known.
By Ronald Katende
The paper introduces MI‑SARSA, an on‑policy temporal‑difference algorithm that incorporates mutual‑information regularization to model bounded rationality in reinforcement learning. By penalizing state‑specific deviations from a learned marginal action prior, the algorithm selectively uses state information only when the expected return outweighs the informational cost, yielding a reward‑complexity tradeoff. MI‑SARSA also predicts reaction times, showing that stronger information penalties lead to simpler policies, lower control costs, and faster responses, while regularization mitigates performance loss after environmental shifts at the expense of asymptotic return.
By James Wu, Chris R. Sims
arXiv:2606. 09858v1 Announce Type: cross Abstract: Robust decision-making requires compression.
By Mark Walsh
arXiv:2603. 02491v3 Announce Type: replace-cross Abstract: As artificial agents become increasingly capable, what internal structure is necessary for an agent to act competently under uncertainty?
By Aran Nayebi