arXiv subjects

Majid Ghasemi

Publications and source records attributed to Majid Ghasemi.

7 recordsLinked to original sources

arXiv2026

Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions

Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior. This is particularly a problem when we are trying to imbue ethical behavior into RL agents. An agent can look ethical on average while concentrating its violations in a few bad episodes, and a creature in the environment harmed in one episode is not restored by good conduct in another. We compare four ways of training ethical behavior in Craftax, an open-ended survival benchmark. The four are: scalar penalties with termination, a linear multi-objective weight sweep, an adaptive Lagrangian constraint, and a non-compensatory utility optimized per episode under the Expected Scalarized Returns (ESR) criterion. All are evaluated under a single detector-based protocol that counts every violation in every episode without censoring. On the frontier of mean return against mean violation rate, the four methods are indistinguishable; per episode they separate sharply. At matched mean return, the ESR agent holds its stated budget of one violation in effectively every episode (worst-decile 1.04 +/- 0.07 violations), the Lagrangian leaks past the same budget (1.14 +/- 0.03), and the weight sweep's worst episodes double it (2.20 +/- 0.20). An observation-augmentation control attributes the separation to the training objective rather than to what the agent observes, and the per-episode guarantee costs nothing on the mean frontier. When ethical violations do not average away across episodes, we argue both training and evaluation must target the per-episode distribution rather than the mean.

cs.LG↗

arXiv2026

Learning When to Trust in Contextual Social Bandits

Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget. We identify a more subtle failure mode that escapes this dichotomy, which we call \emph{Contextual Sycophancy}. In this failure, evaluators are truthful in benign contexts but systematically biased in critical ones, so that no single evaluator is reliable everywhere and the corrupt evaluators may form a \emph{majority} in the contexts that matter. Our first result is an information-theoretic lower bound. We exhibit two problem instances that induce \emph{identical} social-feedback distributions yet have disjoint optimal actions, proving that \emph{any} algorithm relying on social feedback alone (including any robust aggregator, regardless of breakdown point) incurs $\Omega(T)$ latent regret. This shows that breaking contextual sycophancy is impossible without having some information. We then show that a sparse stream of ground-truth audits, available with probability $p_{\mathrm{aud}}$, is sufficient. We propose \ESA, which learns a per-evaluator contextual \emph{trust boundary} from audits and re-weights feedback accordingly, and we prove a high-probability latent-regret bound of $\tilde{\mathcal{O}}\!\big(\sqrt{T\,d_{VC}/p_{\mathrm{aud}}} + d\sqrt{T} + \epsilon_{\mathrm{tol}}T\big)$, where $d_{VC}$ is the complexity of the adversary's bias strategy. The audit-dependence $1/\sqrt{p_{\mathrm{aud}}}$ matches the information-theoretic necessity of audits. Empirically, \ESA\ recovers the ground truth when $80\%$ of the social layer is adversarial, a regime in which median- and mean-based robust baselines fail.

cs.AI↗

arXiv2026

Objective Decoupling in Social Reinforcement Learning: Recovering Ground Truth from Sycophantic Majorities

Contemporary AI alignment strategies rely on a fragile premise: that human feedback, while noisy, remains a fundamentally truthful signal. In this paper, we identify this assumption as Dogma 4 of Reinforcement Learning (RL). We demonstrate that while this dogma holds in static environments, it fails in social settings where evaluators may be sycophantic, lazy, or adversarial. We prove that under Dogma 4, standard RL agents suffer from what we call Objective Decoupling, a structural failure mode where the agent's learned objective permanently separates from the latent ground truth, guaranteeing convergence to misalignment. To resolve this, we propose Epistemic Source Alignment (ESA). Unlike standard robust methods that rely on statistical consensus (trusting the majority), ESA utilizes sparse safety axioms to judge the source of the feedback rather than the signal itself. We prove that this "judging the judges" mechanism guarantees convergence to the true objective, even when a majority of evaluators are biased. Empirically, we show that while traditional consensus methods fail under majority collusion, our approach successfully recovers the optimal policy.

cs.AI↗

arXiv2025

Toward Virtuous Reinforcement Learning: A Critique and Roadmap

This paper critiques common patterns in machine ethics for Reinforcement Learning (RL) and argues for a virtue focused alternative. We highlight two recurring limitations in much of the current literature: (i) rule based (deontological) methods that encode duties as constraints or shields often struggle under ambiguity and nonstationarity and do not cultivate lasting habits, and (ii) many reward based approaches, especially single objective RL, implicitly compress diverse moral considerations into a single scalar signal, which can obscure trade offs and invite proxy gaming in practice. We instead treat ethics as policy level dispositions, that is, relatively stable habits that hold up when incentives, partners, or contexts change. This shifts evaluation beyond rule checks or scalar returns toward trait summaries, durability under interventions, and explicit reporting of moral trade offs. Our roadmap combines four components: (1) social learning in multi agent RL to acquire virtue like patterns from imperfect but normatively informed exemplars; (2) multi objective and constrained formulations that preserve value conflicts and incorporate risk aware criteria to guard against harm; (3) affinity based regularization toward updateable virtue priors that support trait like stability under distribution shift while allowing norms to evolve; and (4) operationalizing diverse ethical traditions as practical control signals, making explicit the value and cultural assumptions that shape ethical RL benchmarks.

cs.AI↗

arXiv2025

Control of ferroelectric domain wall dynamics by point defects: Insights from ab initio based simulations

The control of ferroelectric domain walls and their dynamics on the nanoscale becomes increasingly important for advanced nanoelectronics and novel computing schemes. One common approach to tackle this challenge is the pinning of walls by point defects. The fundamental understanding on how different defects influence the wall dynamics is, however, incomplete. In particular, the important class of defect dipoles in acceptor-doped ferroelectrics is currently underrepresented in theoretical work. In this study, we combine molecular dynamics simulations based on an \textit{ab\ initio}-derived effective Hamiltonian and methods from materials informatics, and analyze the impact of these defects on the motion of 180$^{\circ}$ domain walls in tetragonal BaTiO$_3$. We show how these defects can act as local pinning centers and restoring forces on the domain structure. Furthermore, we reveal how walls can flow around sparse defects by nucleation and growth of dipole clusters, and how pinning, roughening and bending of walls depend on the defect distribution. Surprisingly, the interaction between acceptor dopants and walls is short-ranged. We show that the limiting factor for the nucleation processes underlying wall motion is the defect-free area in front of the wall.

cond-mat.mtrl-sci↗

arXiv2024

A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges

Reinforcement Learning (RL) has emerged as a powerful paradigm in Artificial Intelligence (AI), enabling agents to learn optimal behaviors through interactions with their environments. Drawing from the foundations of trial and error, RL equips agents to make informed decisions through feedback in the form of rewards or penalties. This paper presents a comprehensive survey of RL, meticulously analyzing a wide range of algorithms, from foundational tabular methods to advanced Deep Reinforcement Learning (DRL) techniques. We categorize and evaluate these algorithms based on key criteria such as scalability, sample efficiency, and suitability. We compare the methods in the form of their strengths and weaknesses in diverse settings. Additionally, we offer practical insights into the selection and implementation of RL algorithms, addressing common challenges like convergence, stability, and the exploration-exploitation dilemma. This paper serves as a comprehensive reference for researchers and practitioners aiming to harness the full potential of RL in solving complex, real-world problems.

cs.AI↗

arXiv2024

Introduction to Reinforcement Learning

Reinforcement Learning (RL), a subfield of Artificial Intelligence (AI), focuses on training agents to make decisions by interacting with their environment to maximize cumulative rewards. This paper provides an overview of RL, covering its core concepts, methodologies, and resources for further learning. It offers a thorough explanation of fundamental components such as states, actions, policies, and reward signals, ensuring readers develop a solid foundational understanding. Additionally, the paper presents a variety of RL algorithms, categorized based on the key factors such as model-free, model-based, value-based, policy-based, and other key factors. Resources for learning and implementing RL, such as books, courses, and online communities are also provided. By offering a clear, structured introduction, this paper aims to simplify the complexities of RL for beginners, providing a straightforward pathway to understanding.

cs.AI↗