Search Results for author: Haitham Bou-Ammar

Found 16 papers, 6 papers with code

Bayesian Reward Models for LLM Alignment

no code implementations20 Feb 2024 Adam X. Yang, Maxime Robeyns, Thomas Coste, Jun Wang, Haitham Bou-Ammar, Laurence Aitchison

To ensure that large language model (LLM) responses are helpful and non-toxic, we usually fine-tune a reward model on human preference data.

Language Modelling Large Language Model

Why Can Large Language Models Generate Correct Chain-of-Thoughts?

no code implementations20 Oct 2023 Rasul Tutunov, Antoine Grosnit, Juliusz Ziomek, Jun Wang, Haitham Bou-Ammar

This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting.

Text Generation

Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?

2 code implementations30 Jan 2023 Juliusz Ziomek, Haitham Bou-Ammar

Learning decompositions of expensive-to-evaluate black-box functions promises to scale Bayesian optimisation (BO) to high-dimensional problems.

Bayesian Optimisation

Contextual Causal Bayesian Optimisation

no code implementations29 Jan 2023 Vahan Arsenyan, Antoine Grosnit, Haitham Bou-Ammar

Causal Bayesian optimisation (CaBO) combines causality with Bayesian optimisation (BO) and shows that there are situations where the optimal reward is not achievable if causal knowledge is ignored.

Bayesian Optimisation Multi-Armed Bandits

Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks

1 code implementation11 Jan 2023 Piotr Kicki, Puze Liu, Davide Tateo, Haitham Bou-Ammar, Krzysztof Walas, Piotr Skrzypczyński, Jan Peters

Motion planning is a mature area of research in robotics with many well-established methods based on optimization or sampling the state space, suitable for solving kinematic motion planning.

Motion Planning

Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation

1 code implementation14 Feb 2022 Aivar Sootla, Alexander I. Cowen-Rivers, Taher Jafferjee, Ziyan Wang, David Mguni, Jun Wang, Haitham Bou-Ammar

Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications.

reinforcement-learning Reinforcement Learning (RL) +1

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

no code implementations ICLR 2022 Hang Ren, Aivar Sootla, Taher Jafferjee, Junxiao Shen, Jun Wang, Haitham Bou-Ammar

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c) Markovian context evolution.

reinforcement-learning Reinforcement Learning (RL) +1

Compositional ADAM: An Adaptive Compositional Solver

no code implementations10 Feb 2020 Rasul Tutunov, Minne Li, Alexander I. Cowen-Rivers, Jun Wang, Haitham Bou-Ammar

In this paper, we present C-ADAM, the first adaptive solver for compositional problems involving a non-linear functional nesting of expected values.

Meta-Learning

Learning High-level Representations from Demonstrations

no code implementations19 Feb 2018 Garrett Andersen, Peter Vrancx, Haitham Bou-Ammar

A common approach to HL, is to provide the agent with a number of high-level skills that solve small parts of the overall problem.

Montezuma's Revenge Open-Ended Question Answering +1

Balancing Two-Player Stochastic Games with Soft Q-Learning

no code implementations9 Feb 2018 Jordi Grau-Moya, Felix Leibfried, Haitham Bou-Ammar

Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers.

Q-Learning Reinforcement Learning (RL) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.