Search Results for author:
Found 15 papers, 4 papers with code
Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment
Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) to human preferences at the time of decoding.
On the True Distribution Approximation of Minimum Bayes-Risk Decoding
Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation.
Return-Aligned Decision Transformer
Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return.
Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding
We propose two variants of MBR, Diverse MBR (DMBR) and $k$-medoids MBR (KMBR), methods to generate a set of sentences with high quality and diversity.
Model-Based Minimum Bayes Risk Decoding
MBR decoding selects a hypothesis from a pool of hypotheses that has the least expected risk under a probability model according to a given utility function.
Policy Gradient with Kernel Quadrature
Reward evaluation of episodes becomes a bottleneck in a broad range of reinforcement learning tasks.
On the Depth between Beam Search and Exhaustive Search for Text Generation
To this end, we introduce Lookahead Beam Search (LBS), a multi-step lookahead search that optimizes the objective considering a fixed number of future steps.
Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative
One way to estimate rewards from collected data is to train the reward estimator and dialog policy simultaneously using adversarial learning (AL).
Safe Collaborative Filtering
Excellent tail performance is crucial for modern machine learning tasks, such as algorithmic fairness, class imbalance, and risk-sensitive decision making, as it ensures the effective handling of challenging samples within a dataset.
Policy Gradient Algorithms with Monte-Carlo Tree Search for Non-Markov Decision Processes
However, since the standard MCTS does not have the ability to learn state representation, the size of the tree-search space can be too large to search.
Mean-Variance Efficient Reinforcement Learning by Expected Quadratic Utility Maximization
To achieve this purpose, we train an agent to maximize the expected quadratic utility function, a common objective of risk management in finance and economics.
Visual analytics for team-based invasion sports with significant events and Markov reward process
To solve this problem, we consider a whole match as a Markov chain of significant events, so that event values can be estimated with a continuous parameter space by solving the Markov chain with a machine learning model.
Sampler for Composition Ratio by Markov Chain Monte Carlo
The key points of our approach are (1) designing an appropriate target distribution by using a condition on the number of nonzero elements, and (2) changing values only between a certain pair of elements in each iteration.
Solving inverse problem of Markov chain with partial observations
The Markov chain is a convenient tool to represent the dynamics of complex systems such as traffic and social systems, where probabilistic transition takes place between internal states.
A Generalized Natural Actor-Critic Algorithm
In this paper, we describe a generalized Natural Gradient (gNG) by linearly interpolating the two FIMs and propose an efficient implementation for the gNG learning based on a theory of the estimating function, generalized Natural Actor-Critic (gNAC).
