Pith. sign in

REVIEW 2 cited by

Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.13609 v3 pith:KLMNF6K3 submitted 2024-05-22 cs.LG q-fin.CPquant-ph

classification cs.LGq-fin.CPquant-ph
keywords decisionmdpsrewardsexpectedlearningncmdpsprocessesreinforcement
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Markov decision processes (MDPs) are used to model a wide variety of applications ranging from game playing over robotics to finance. Their optimal policy typically maximizes the expected sum of rewards given at each step of the decision process. However, a large class of problems does not fit straightforwardly into this framework: Non-cumulative Markov decision processes (NCMDPs), where instead of the expected sum of rewards, the expected value of an arbitrary function of the rewards is maximized. Example functions include the maximum of the rewards or their mean divided by their standard deviation. In this work, we introduce a general mapping of NCMDPs to standard MDPs. This allows all techniques developed to find optimal policies for MDPs, such as reinforcement learning or dynamic programming, to be directly applied to the larger class of NCMDPs. Focusing on reinforcement learning, we show applications in a diverse set of tasks, including classical control, portfolio optimization in finance, and discrete optimization problems. Given our approach, we can improve both final performance and training time compared to relying on standard MDPs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Optimising entanglement distribution policies under classical communication constraints assisted by reinforcement learning

    quant-ph 2024-12 conditional novelty 6.0 of 10

    For quantum repeater chains with classical communication delays, predictive and reinforcement-learning policies that act on partial information deliver end-to-end entanglement faster than wait-for-broadcast swap-asap ...

  2. Recursive Reward Aggregation

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Recursive reward aggregation defines Bellman equations for any objective computable by folding rewards, enabling RL agents to optimize max, min, mean, variance, and Sharpe ratio without reward redesign.

Pith tools