Skip to content
Log in
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt

Category

reinforcement learning

2,442 papers

#reinforcement learning Oct 2026

Comparing Stochastic Training Environments for Deep Reinforcement Learning with Deep Q-network: Learning Stability and Transfer to Real Data

The paper investigates how the choice of a generative stochastic model of the training environment affects the numerical stability of the learning and the transfer of the Double DQN policy to real time series. Four environments — GBM, GARCH(1,1)-t, Minimal Neural SDE, and Neural Jump-Diffusion — are compared, created o...

Sergey Leonov · 0 citations
#reinforcement learning Oct 2026

Designing for the Intentional Stance: Stance Misalignment, Value Alignment, and the Case for Care Ethics in Human-LLM Relationships (Extended Abstract)

Users are increasingly forming emotionally charged relation-ships with general-purpose large language models (LLMs), producing documented patterns of dependency, relational harm, and affective disappointment. Existing value alignment frameworks, including Reinforcement Learning from Human Feedback, Constitutional AI, a...

Rayane El Masri, Aaron Snoswell, Ehsan Dehghan · 0 citations
#reinforcement learning Open access Oct 2026

Decision Theory and Artificial Intelligence: An Anatomical Review of Output Contracts, Acquisition Geometries, and Epistemic Verticals

This paper presents a detailed anatomical review of Miquel Noguer i Alonso's "Decision Theory and Artificial Intelligence" (2026). The reviewed work develops a unified Bayesian decision-theoretic framework that links feasible action spaces, reward functions, statistical estimation targets, and costly information acquis...

Syed Muntasir Mamun · 0 citations
#reinforcement learning Oct 2026

Virtue by Observation: Social Reinforcement Learning for Intrinsically Ethical Agents

Reinforcement learning is increasingly deployed in settings with ethical stakes, yet rule-based and scalar-reward alignment approaches remain brittle and prone to proxy gaming. I argue that two of their most persistent failures, hallucination and moral drift, share a single structural cause, which I term \textit{feedba...

Majid Ghasemi · 0 citations
#reinforcement learning Oct 2026

Survival-aware self-play reinforcement learning for partially observable beyond visual range air combat

We present a recurrent self-play reinforcement learning framework for autonomous beyond-visual-range (BVR) air combat under partial observability. The environment is formulated as a decision-level BVR missile-duel simulator that combines 3-DoF aircraft kinematics, field-of-view radar observation, track-quality decay, f...

Lianqun Zhang, Jingwei Zhao, Yu Zhang · 0 citations
#reinforcement learning Oct 2026

Rules or Character? Scaling Laws for AI Safety Design (Extended Abstract)

Artificial Intelligence (AI) safety systems combine character shaping (e.g., Reinforcement Learning from Human Feedback [RLHF], Constitutional AI), which modifies behavioral distributions at training time, with rule enforcement (e.g., output filters, safety classifiers), which blocks harmful outputs at inference time,...

Satoshi Takahashi, Nobuji Kouno, Masaaki Komatsu et al. · 0 citations
#reinforcement learning Open access Oct 2026

Autonomous Resource Allocation for QoS Enhancement in Next-Generation Heterogeneous Wireless Systems

The network heterogeneity, high dynamism of traffic demands, channel conditions and diverse Quality-of-Service (QoS) requirements in Beyond Fifth-Generation (B5G) and Sixth-Generation (6G) heterogeneous wireless networks create new difficulties for autonomous resource allocation. Static and reactive methods are not ada...

Jafaar Fahad A. Rida, Elaf Noori Saddam, Basim Abood · 0 citations
#reinforcement learning Open access Oct 2026

Dynamic dopamine signaling, prediction error, and microcircuit mechanisms in stress-induced depression-like behaviors

Chronic stress contributes to major depressive disorder (MDD) phenotypes by disrupting coordinated neuromodulatory systems and their corresponding computational frameworks. In this review, we explore how the dynamic interplay of ventral tegmental area dopamine (DA) signaling, microcircuit gating, and prediction error m...

Ashraf Mahmud, Ljupcho Efremov · 0 citations
#reinforcement learning Oct 2026

Beneficiary-Based Responsibility for AI Training Labour: Lessons from Kenya’s Gig Economy and Beyond

AI systems are built from large volumes of outsourced human labour, including data annotation, content moderation, and reinforcement learning feedback. Much of this work is performed in low-and middle-income countries under conditions of low pay, insecure contracts, psychological harm, and weak legal protection. Existi...

Ruoyi Lu, Brenda Maina · 0 citations
#reinforcement learning Oct 2026

Diet: Interpreting Ethical Tradeoffs in Disrupted Sociotechnical Systems

Sociotechnical systems comprise human stakeholders and autonomous agents, where stakeholders may prioritize values (such as freedom, security, and welfare) differently. Social norms operationalize these values by specifying expectations about acceptable behavior. Disruptions in sociotechnical systems create situations...

Divya Sundaresan, Gordon Briggs, Munindar P. Singh · 0 citations
#reinforcement learning Oct 2026

The Forager’s Dilemma: Peer Enforcement Alone Is Not Enough for Stable Multi-Agent Alignment

AI alignment methods typically rely on one of two strategies, either optimizing a scalar reward proxy learned from human feedback or situating agents in social environments where peer critique provides a dynamic correction signal. We argue that both strategies, taken in isolation, are structurally unstable. Static scal...

Majid Ghasemi, Prabhjyot Singh, Mark Crowley · 0 citations
#reinforcement learning Oct 2026

Trajectory-Constrained Feature Transformation Optimization Framework for Stable Tabular Data Reprogramming

Tabular data reprogramming is a cornerstone of Data-Centric AI, which seeks to mathematically reconfigure raw features into more expressive and model-efficient representations. This process has traditionally relied on extensive manual engineering. Further, recent automated feature transformation approaches treat each t...

Xiaohan Huang, Dongjie Wang, Zhiyuan Ning et al. · 0 citations

From tech blogs

See all →
MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.