English
Related papers

Related papers: How to Learn a Useful Critic? Model-based Action-G…

200 papers

Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence…

Machine Learning · Computer Science 2019-07-16 Zhuoran Yang , Yongxin Chen , Mingyi Hong , Zhaoran Wang

We propose a novel actor-critic algorithm with guaranteed convergence to an optimal policy for a discounted reward Markov decision process. The actor incorporates a descent direction that is motivated by the solution of a certain non-linear…

Machine Learning · Computer Science 2015-07-30 Prashanth L. A. , H. L. Prasad , Shalabh Bhatnagar , Prakash Chandra

Decision-making agents with planning capabilities have achieved huge success in the challenging domain like Chess, Shogi, and Go. In an effort to generalize the planning ability to the more general tasks where the environment dynamics are…

Artificial Intelligence · Computer Science 2020-06-23 Xuxi Yang , Werner Duvaud , Peng Wei

Decentralized (PO)MDPs provide an expressive framework for sequential decision making in a multiagent system. Given their computational complexity, recent research has focused on tractable yet practical subclasses of Dec-POMDPs. We address…

Artificial Intelligence · Computer Science 2018-04-11 Duc Thien Nguyen , Akshat Kumar , Hoong Chuin Lau

Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the…

Machine Learning · Computer Science 2023-03-02 Samuel Neumann , Sungsu Lim , Ajin Joseph , Yangchen Pan , Adam White , Martha White

Many reality tasks such as robot coordination can be naturally modelled as multi-agent cooperative system where the rewards are sparse. This paper focuses on learning decentralized policies for such tasks using sub-optimal demonstration. To…

Artificial Intelligence · Computer Science 2021-08-20 Peixi Peng , Junliang Xing

Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination reliably. Ideally, agents should learn and execute…

Machine Learning · Computer Science 2022-10-12 Yuchen Xiao , Weihao Tan , Christopher Amato

This scientific paper propose a novel portfolio optimization model using an improved deep reinforcement learning algorithm. The objective function of the optimization model is the weighted sum of the expectation and value at risk(VaR) of…

Machine Learning · Computer Science 2022-08-30 Boyi Jin

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…

Machine Learning · Computer Science 2018-06-20 Shangda Li , Selina Bing , Steven Yang

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample…

Machine Learning · Computer Science 2019-09-18 Zac Wellmer , James Kwok

We develop policy gradients methods for stochastic control with exit time in a model-free setting. We propose two types of algorithms for learning either directly the optimal policy or by learning alternately the value function (critic) and…

Computational Finance · Quantitative Finance 2023-02-16 Mohamed Hamdouche , Pierre Henry-Labordere , Huyen Pham

Traditional continuous deep reinforcement learning (RL) algorithms employ deterministic or unimodal Gaussian actors, which cannot express complex multimodal decision distributions. This limitation can hinder their performance in…

Machine Learning · Computer Science 2025-11-04 Ziqi Wang , Jiashun Liu , Ling Pan

Model-based reinforcement learning has the potential to be more sample efficient than model-free approaches. However, existing model-based methods are vulnerable to model bias, which leads to poor generalization and asymptotic performance…

Machine Learning · Computer Science 2019-06-27 Tung-Long Vuong , Kenneth Tran

In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong…

Machine Learning · Computer Science 2026-05-26 Safwan Labbi , Paul Mangold , Daniil Tiapkin , Eric Moulines

We propose a new objective, the counterfactual objective, unifying existing objectives for off-policy policy gradient algorithms in the continuing reinforcement learning (RL) setting. Compared to the commonly used excursion objective, which…

Machine Learning · Computer Science 2019-10-29 Shangtong Zhang , Wendelin Boehmer , Shimon Whiteson

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for…

Machine Learning · Computer Science 2018-10-16 Ilya Kostrikov , Kumar Krishna Agrawal , Debidatta Dwibedi , Sergey Levine , Jonathan Tompson

We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each…

Multiagent Systems · Computer Science 2021-11-02 Kuo Li , Qing-Shan Jia

Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learning. Many such methods take the form of actor-critic with…

Machine Learning · Computer Science 2022-05-26 Xueguang Lyu , Andrea Baisero , Yuchen Xiao , Christopher Amato

We revisit the standard formulation of tabular actor-critic algorithm as a two time-scale stochastic approximation with value function computed on a faster time-scale and policy computed on a slower time-scale. This emulates policy…

Machine Learning · Computer Science 2024-06-21 Shalabh Bhatnagar , Vivek S. Borkar , Soumyajit Guin

While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the associated high-dimensional action spaces. However, most…

Machine Learning · Computer Science 2023-09-27 Tim Seyde , Peter Werner , Wilko Schwarting , Igor Gilitschenski , Martin Riedmiller , Daniela Rus , Markus Wulfmeier