paper-with-me

Papers

Optimizing Return Distributions with Distributional Dynamic Programming

2025-01-22 · Bernardo Ávila Pires, Mark Rowland, Diana Borsa, Zhaohan Daniel Guo, Khimya Khetarpal, André Barreto, David Abel, Rémi Munos, Will Dabney

We introduce distributional dynamic programming (DP) methods for optimizing statistical functionals of the return distribution, with standard reinforcement learning as a special case. Previous distributional DP methods could optimize the same class of expected utilities as classic DP. To go beyond expected utilities, we combine distributional DP with stock augmentation, a technique previously introduced for classic DP in the context of risk-sensitive RL, where the MDP state is augmented with a statistic of the rewards obtained so far (since the first time step). We find that a number of recently studied problems can be formulated as stock-augmented return distribution optimization, and we show that we can use distributional DP to solve them. We analyze distributional value and policy iteration, with bounds and a study of what objectives these distributional DP methods can or cannot optimize. We describe a number of applications outlining how to use distributional DP to solve different stock-augmented return distribution optimization problems, for example maximizing conditional value-at-risk, and homeostatic regulation. To highlight the practical potential of stock-augmented return distribution optimization and distributional DP, we combine the core ideas of distributional value iteration with the deep RL agent DQN, and empirically evaluate it for solving instances of the applications discussed.

📄 PDF Abstract BibTeX arXiv:2501.13028

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
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…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

Distributional Bellman Operators over Mean Embeddings

2023-12-09 · Li Kevin Wenliang, Grégoire Delétang, Matthew Aitchison, Marcus Hutter 외

We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several new algorithms for dynamic programming a…

Atari GamesDeep Reinforcement LearningDistributional Reinforcement Learningreinforcement-learning+1

On Policy Evaluation Algorithms in Distributional Reinforcement Learning

2024-07-19 · Julian Gerstenberg, Ralph Neininger, Denis Spiegel

We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL). The proposed distributional dynamic pro…

Distributional Reinforcement Learningreinforcement-learningReinforcement Learning

StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning

2026-04-09 · Ivo Nowak arxiv

Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-difference errors without explicitly exploiting global structure. In contrast, …

Reinforcement Learning

On solutions of the distributional Bellman equation

2022-01-31 · Julian Gerstenberg, Ralph Neininger, Denis Spiegel

In distributional reinforcement learning not only expected returns but the complete return distributions of a policy are taken into account. The return distribution for a fixed policy is given as the solution of an assoc…

Distributional Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Robustness and risk management via distributional dynamic programming

2021-12-28 · Mastane Achab, Gergely Neu

In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (M…

Distributional Reinforcement LearningManagementreinforcement-learningReinforcement Learning+1