English
Related papers

Related papers: Geometry of Policy Improvement

200 papers

We present an efficient algorithm for model-free episodic reinforcement learning on large (potentially continuous) state-action spaces. Our algorithm is based on a novel $Q$-learning policy with adaptive data-driven discretization. The…

Machine Learning · Computer Science 2019-12-20 Sean R. Sinclair , Siddhartha Banerjee , Christina Lee Yu

We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used…

Machine Learning · Computer Science 2023-07-21 Zhiao Huang , Litian Liang , Zhan Ling , Xuanlin Li , Chuang Gan , Hao Su

Although data augmentation is a powerful technique for improving the performance of image classification tasks, it is difficult to identify the best augmentation policy. The optimal augmentation policy, which is the latent variable, cannot…

Computer Vision and Pattern Recognition · Computer Science 2023-05-05 Koichi Kuriyama

Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing…

Machine Learning · Computer Science 2026-02-05 Kyuseong Choi , Dwaipayan Saha , Woojeong Kim , Anish Agarwal , Raaz Dwivedi

We consider deterministic finite-horizon optimal control problems with a fixed initial state. We introduce an on-line policy iteration method, which, starting from a given policy, however obtained, generates a sequence of cost-improving…

Systems and Control · Electrical Eng. & Systems 2026-05-12 Yuchao Li , Fei Chen , Yingke Li , Chuchu Fan , Dimitri Bertsekas

This paper proposes a formal approach to online learning and planning for agents operating in a priori unknown, time-varying environments. The proposed method computes the maximally likely model of the environment, given the observations…

Machine Learning · Computer Science 2021-02-09 Melkior Ornik , Ufuk Topcu

Policy optimization (PO) algorithms are used to refine Large Language Models for complex, multi-step reasoning. Current state-of-the-art pipelines enforce a strict think-then-answer format to elicit chain-of-thought (CoT); however, the…

Computation and Language · Computer Science 2025-10-28 Debdeep Sanyal , Aakash Sen Sharma , Dhruv Kumar , Saurabh Deshpande , Murari Mandal

A sequence of social sensors estimate an unknown parameter (modeled as a state of nature) by performing Bayesian Social Learning, and myopically optimize individual reward functions. The decisions of the social sensors contain quantized…

Social and Information Networks · Computer Science 2020-03-31 Sujay Bhatt , Vikram Krishnamurthy

In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or…

Machine Learning · Computer Science 2016-06-17 Jonathan Ho , Jayesh K. Gupta , Stefano Ermon

We study the problem of identifying the policy space of a learning agent, having access to a set of demonstrations generated by its optimal policy. We introduce an approach based on statistical testing to identify the set of policy…

Machine Learning · Computer Science 2019-09-10 Alberto Maria Metelli , Guglielmo Manneschi , Marcello Restelli

Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based…

Artificial Intelligence · Computer Science 2017-11-23 Daniel Levy , Stefano Ermon

In this technical note, we establish an upper-bound on the threshold on the discount factor starting from which all discounted-optimal deterministic policies are gain-optimal, that we prove to be tight on an example. To address…

Systems and Control · Electrical Eng. & Systems 2023-04-18 Victor Boone

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

Machine Learning · Computer Science 2015-09-24 Marvin Zhang , Zoe McCarthy , Chelsea Finn , Sergey Levine , Pieter Abbeel

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision…

We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove…

Machine Learning · Computer Science 2011-05-02 Shie Mannor , John Tsitsiklis

The famous Policy Iteration algorithm alternates between policy improvement and policy evaluation. Implementations of this algorithm with several variants of the latter evaluation stage, e.g, $n$-step and trace-based returns, have been…

Artificial Intelligence · Computer Science 2018-08-01 Yonathan Efroni , Gal Dalal , Bruno Scherrer , Shie Mannor

Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement…

Artificial Intelligence · Computer Science 2018-07-05 Artem Molchanov , Karol Hausman , Stan Birchfield , Gaurav Sukhatme

There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and…

Machine Learning · Computer Science 2013-01-14 Lex Weaver , Nigel Tao

In consequential domains, it is often impossible to compel individuals to take treatment, so that optimal policy rules are merely suggestions in the presence of human non-adherence to treatment recommendations. We study personalized…

Machine Learning · Computer Science 2026-04-24 Angela Zhou

It is of significance for an agent to learn a widely applicable and general-purpose policy that can achieve diverse goals including images and text descriptions. Considering such perceptually-specific goals, the frontier of deep…

Machine Learning · Computer Science 2021-12-14 Jinxin Liu , Donglin Wang , Qiangxing Tian , Zhengyu Chen