English
Related papers

Related papers: Accelerating Value Iteration with Anchoring

200 papers

In reinforcement learning the Q-values summarize the expected future rewards that the agent will attain. However, they cannot capture the epistemic uncertainty about those rewards. In this work we derive a new Bellman operator with…

Machine Learning · Computer Science 2022-12-07 Brendan O'Donoghue

Policy evaluation is an important instrument for the comparison of different algorithms in Reinforcement Learning (RL). However, even a precise knowledge of the value function $V^{\pi}$ corresponding to a policy $\pi$ does not provide…

Machine Learning · Computer Science 2026-01-21 Denis Belomestny , Ilya Levin , Alexey Naumov , Sergey Samsonov

Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired behavior in Neural…

Machine Learning · Computer Science 2023-04-21 Steffen Gracla , Edgar Beck , Carsten Bockelmann , Armin Dekorsy

Processes (MDPs) often require frequent decision making, that is, taking an action every microsecond, second, or minute. Infinite horizon discount reward formulation is still relevant for a large portion of these applications, because…

Optimization and Control · Mathematics 2014-12-17 Yin-Lam Chow , Junjie Qin

This paper studies an accelerated fitted value iteration (FVI) algorithm to solve high-dimensional Markov decision processes (MDPs). FVI is an approximate dynamic programming algorithm that has desirable theoretical properties. However, it…

Optimization and Control · Mathematics 2020-11-30 Sixiang Zhao , William B. Haskell , Michel-Alexandre Cardin

In reinforcement learning (RL), aligning agent behavior with specific objectives typically requires careful design of the reward function, which can be challenging when the desired objectives are complex. In this work, we propose an…

Machine Learning · Computer Science 2025-09-05 Yuting Tang , Yivan Zhang , Johannes Ackermann , Yu-Jie Zhang , Soichiro Nishimori , Masashi Sugiyama

Gradient-based methods for value estimation in reinforcement learning have favorable stability properties, but they are typically much slower than Temporal Difference (TD) learning methods. We study the root causes of this slowness and show…

Machine Learning · Computer Science 2023-07-25 Arsalan Sharifnassab , Richard Sutton

Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on…

Artificial Intelligence · Computer Science 2026-05-14 Wo Wei Lin , Ethan Rathbun , Enrico Marchesini Xiang Zhi Tan

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of…

Machine Learning · Computer Science 2025-10-28 Ran Levinstein , Amit Attia , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Itay Evron

We consider the problem of reinforcement learning using function approximation, where the approximating basis can change dynamically while interacting with the environment. A motivation for such an approach is maximizing the value function…

Machine Learning · Computer Science 2010-05-04 Dotan Di Castro , Shie Mannor

In the paper, we design a novel Bregman gradient policy optimization framework for reinforcement learning based on Bregman divergences and momentum techniques. Specifically, we propose a Bregman gradient policy optimization (BGPO) algorithm…

Machine Learning · Computer Science 2022-03-17 Feihu Huang , Shangqian Gao , Heng Huang

Value aggregation is a general framework for solving imitation learning problems. Based on the idea of data aggregation, it generates a policy sequence by iteratively interleaving policy optimization and evaluation in an online learning…

Machine Learning · Computer Science 2018-01-24 Ching-An Cheng , Byron Boots

Sampling efficiency is a key bottleneck in reinforcement learning with verifiable rewards. Existing group-based policy optimization methods, such as GRPO, allocate a fixed number of rollouts for all training prompts. This uniform allocation…

Machine Learning · Computer Science 2026-03-06 Hieu Trung Nguyen , Bao Nguyen , Wenao Ma , Yuzhi Zhao , Ruifeng She , Viet Anh Nguyen

This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents.…

Machine Learning · Computer Science 2010-10-04 Joel Veness , Kee Siong Ng , Marcus Hutter , David Silver

The naive application of Reinforcement Learning algorithms to continuous control problems -- such as locomotion and manipulation -- often results in policies which rely on high-amplitude, high-frequency control signals, known colloquially…

Robotics · Computer Science 2019-02-14 Steven Bohez , Abbas Abdolmaleki , Michael Neunert , Jonas Buchli , Nicolas Heess , Raia Hadsell

In a probabilistic latent variable model, factorized (or mean-field) variational inference (F-VI) fits a separate parametric distribution for each latent variable. Amortized variational inference (A-VI) instead learns a common inference…

Machine Learning · Statistics 2024-05-27 Charles C. Margossian , David M. Blei

Algorithmic analysis of Markov decision processes (MDP) and stochastic games (SG) in practice relies on value-iteration (VI) algorithms. Since the basic version of VI does not provide guarantees on the precision of the result, variants of…

Computer Science and Game Theory · Computer Science 2026-03-31 Muqsit Azeem , Jan Kretinsky , Maximilian Weininger

In this paper we show that a simple, data dependent way of setting the initial vector can be used to substantially speed up the training of linear one-versus-all (OVA) classifiers in extreme multi-label classification (XMC). We discuss the…

Machine Learning · Computer Science 2021-09-28 Erik Schultheis , Rohit Babbar

A new gradient-based optimization approach by automatically scheduling the learning rate has been proposed recently, which is called Binary Forward Exploration (BFE). The Adaptive version of BFE has also been discussed thereafter. In this…

Machine Learning · Computer Science 2022-09-23 Xin Cao

In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model…

Machine Learning · Computer Science 2024-12-02 Xingyu Xie , Pan Zhou , Huan Li , Zhouchen Lin , Shuicheng Yan
‹ Prev 1 8 9 10 Next ›