paper-with-me

Papers

On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics

2023-10-30 · Michal Nauman, Marek Cygan

Risk-aware Reinforcement Learning (RL) algorithms like SAC and TD3 were shown empirically to outperform their risk-neutral counterparts in a variety of continuous-action tasks. However, the theoretical basis for the pessimistic objectives these algorithms employ remains unestablished, raising questions about the specific class of policies they are implementing. In this work, we apply the expected utility hypothesis, a fundamental concept in economics, to illustrate that both risk-neutral and risk-aware RL goals can be interpreted through expected utility maximization using an exponential utility function. This approach reveals that risk-aware policies effectively maximize value certainty equivalent, aligning them with conventional decision theory principles. Furthermore, we propose Dual Actor-Critic (DAC). DAC is a risk-aware, model-free algorithm that features two distinct actor networks: a pessimistic actor for temporal-difference learning and an optimistic actor for exploration. Our evaluations of DAC across various locomotion and manipulation tasks demonstrate improvements in sample efficiency and final performance. Remarkably, DAC, while requiring significantly less computational resources, matches the performance of leading model-based methods in the complex dog and humanoid domains.

📄 PDF Abstract BibTeX arXiv:2310.19527

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Target Policy Smoothing Target Policy Smoothing is a regularization strategy for the value function in reinforcement learning. Deterministic policies can overfit to narrow peaks in the value…
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Clipped Double Q-learning 설명 없음
TD3 TD3 builds on the DDPG algorithm for reinforcement learning, with a couple of modifications aimed at tackling overestimation bias…

Similar Papers 제목 키워드 기반

Risk-Sensitive Exponential Actor Critic

2026-02-06 · Alonso Granados, Jason Pacheco arxiv

Model-free deep reinforcement learning (RL) algorithms have achieved tremendous success on a range of challenging tasks. However, safety concerns remain when these methods are deployed on real-world applications, necessi…

Reinforcement Learning

Risk Awareness in HTN Planning

2022-04-22 · Ebaa Alnazer, Ilche Georgievski, Marco Aiello

Actual real-world domains are characterised by uncertain situations in which acting and use of resources require embracing risk. Performing actions in such domains always entails costs of consuming some resource, such as…

Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets

2021-07-16 · Yue Gao, Kry Yik Chau Lui, Pablo Hernandez-Leal

Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and costly exploration. Moreover, markets are in…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning

2025-10-03 · Juan Sebastian Rojas, Chi-Guhn Lee arxiv

Continual reinforcement learning (continual RL) seeks to formalize the notions of lifelong learning and endless adaptation in RL. In particular, the aim of continual RL is to develop RL agents that can maintain a careful…

Reinforcement LearningContinual Learning

Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory

2023-08-24 · Karthik Somayaji NS, Yu Wang, Malachi Schram, Jan Drgona 외

Risk-sensitive reinforcement learning (RL) has garnered significant attention in recent years due to the growing interest in deploying RL agents in real-world scenarios. A critical aspect of risk awareness involves model…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)