arXiv research

New reward function improves GAIL performance in task-based environments.

Bayesian Robust Optimization for Imitation Learning (BROIL) balances risk and reward.

AlphaZeroBeta uses deep reinforcement learning for market-neutral portfolios, outperforming traditional methods.

Online learning has traditionally focused on the expected rewards. In this paper, a risk-averse online learning problem under the performance measure of the mean-variance of the rewards is studied. Both the bandit and full information settings are considered. The performance of several existing policies is analyzed, an…

Study optimal stopping for variable annuity contracts with discontinuous rewards.

The paper has 2 main goals: 1. We propose a variant of the CAPM based on coherent risk. 2. In addition to the real-world measure and the risk-neutral measure, we propose the third one: the extreme measure. The introduction of this measure provides a powerful tool for investigating the relation between the first two mea…

We implement momentum strategies using reward-risk measures as ranking criteria based on classical tempered stable distribution. Performances and risk characteristics for the alternative portfolios are obtained in various asset classes and markets. The reward-risk momentum strategies with lower volatility levels outper…

The paper addresses human-like decision-making in multi-agent systems using bounded risk-sensitive Markov Games.

Unified framework for risk-aware policy learning in contextual bandits.

Generative model uses DDPMs for risk-neutral derivative pricing.

New method separates model and non-model risks for more practical asset pricing.

The paper bounds payoffs and option prices in discrete models.

Neural nets optimize dynamic hedging strategies with transaction costs.

Proposes a method to construct risk-neutral marginals from arbitrage-free option prices.

Efficient RL in partially observable risk-sensitive environments with hindsight observations.

MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.

Characterizes neutral deformation modes of minimal surfaces.

Paper introduces benchmark-neutral pricing for long-term contracts.

The paper studies nilpotent structures in oriented neutral vector bundles and neutral hyperKähler structures.

Study finds all 4D neutral manifolds.

The purpose of this article is to review some recent results on the geometry of neutral signature metrics in dimension four and their twistor spaces. The following topics are considered: Neutral Kähler and hyperkähler surfaces, Walker metrics, Neutral anti-self-dual 4-manifolds and projective structures, Twistor spaces…

Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes that reflect social constructs. To address this concern, in this paper, we propo…

Currently, machine learning plays an important role in the lives and individual activities of numerous people. Accordingly, it has become necessary to design machine learning algorithms to ensure that discrimination, biased views, or unfair treatment do not result from decision making or predictions made via machine le…

Unified methods for hedging impermanent loss in decentralized exchanges.

Classical multi-armed bandit problems use the expected value of an arm as a metric to evaluate its goodness. However, the expected value is a risk-neutral metric. In many applications like finance, one is interested in balancing the expected return of an arm (or portfolio) with the risk associated with that return. In …

Optimizes risk-neutral probabilities for derivative pricing.

Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learn…

This work characterizes reward function partial identifiability and its impact on policy optimization.

This paper considers aspects of 4-manifold topology from the point of view of the null cone of a neutral metric, a point of view we call neutral causal topology. In particular, we construct and investigate neutral 4-manifolds with null boundaries that arise from canonical 3- and 4-dimensional settings. A null hypersurf…

The paper shows how to calculate risk-neutral default probabilities from bid and ask CDS quotes.

Simulates risk-neutral markets using neural spline flows.

New concept: reward hacking, where optimizing a flawed reward function can hurt performance.

We present a novel method for learning a set of disentangled reward functions that sum to the original environment reward and are constrained to be independently obtainable. We define independent obtainability in terms of value functions with respect to obtaining one learned reward while pursuing another learned reward…

Enhances reward specification in RL with a novel language-based approach.

The paper proposes a new method to estimate interest rates consistently under both risk-neutral and real-world measures.

EPIC quantifies reward differences without policy optimization.

New algorithm for reward-free RL with linear function approximation, reducing sample complexity.

The study finds that specific distributions can be used for risk-neutral valuation in Heston's SV model.

New lower bounds for combinatorial multi-armed bandits for general reward functions.

Designers of AI agents often iterate on the reward function in a trial-and-error process until they get the desired behavior, but this only guarantees good behavior in the training environment. We propose structuring this process as a series of queries asking the user to compare between different reward functions. Thus…

The aim of this paper is to give examples of compact neutral 4-manifolds $(M,g)$ whose Ricci tensor $ρ$ satisfies the relation $\nabla_Xρ(X,X) =\frac13Xτg(X,X)$. We present also a family of new Einstein bi-Hermitian neutral metrics on ruled surfaces of genus $g>1$.

The paper shows that benchmark-neutral pricing minimizes option prices.

Project estimates risk-neutral dependence from option prices.

PQR estimates reward functions from actions and states without assuming state-only rewards.

In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design problem, or close variants thereof, have been proposed in the literature. In this…

Paper proposes operator deep Q-learning for quick reward adaptation.

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task objective. This gives rise to the agent alignment problem: how do we create age…

Paper studies pricing and hedging of nonreplicable insurance contracts using benchmark-neutral approach.