The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Traditional methods, such as Reinforcement Learning from Human Feedback (RLHF), achieve alignment by fine-tuning model parameters, but these approaches are often computationally expensive and impractical when models are frozen or inaccessible for parameter modification. In contrast, in this work, we consider prompt optimization as a viable alternative to RLHF for LLM alignment, leveraging the fact that the output of an LLM is a direct function of its input prompt. While prompt optimization has shown empirical promise, its theoretical underpinning remains under-explored. To address this gap, we propose Align Pro, a unified theoretical framework consists of a prompter, designed to rigorously study LLM alignment via prompt optimization. To analyze the prompt optimization process, we derive a closed-form expression for the optimal prompter distribution, and establish theoretical bounds that compare the performance of prompt optimization against RLHF-based fine-tuning. Finally, we provide empirical validation through experiments on the IMDB dataset, demonstrating that prompt optimization can effectively align LLMs, even when parameter fine-tuning is not feasible.

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment

We propose a novel combinatorial stochastic-greedy bandit (SGB) algorithm for combinatorial multi-armed bandit problems when no extra information other than the joint reward of the selected set of $n$ arms at each time step $t\in [T]$ is observed. SGB adopts an optimized stochastic-explore-then-commit approach and is specifically designed for scenarios with a large set of base arms. Unlike existing methods that explore the entire set of unselected base arms during each selection step, our SGB algorithm samples only an optimized proportion of unselected arms and selects actions from this subset. We prove that our algorithm achieves a $(1-1/e)$-regret bound of $\mathcal{O}(n^{\frac{1}{3}} k^{\frac{2}{3}} T^{\frac{2}{3}} \log(T)^{\frac{2}{3}})$ for monotone stochastic submodular rewards, which outperforms the state-of-the-art in terms of the cardinality constraint $k$. Furthermore, we empirically evaluate the performance of our algorithm in the context of online constrained social influence maximization. Our results demonstrate that our proposed approach consistently outperforms the other algorithms, increasing the performance gap as $k$ grows.

Combinatorial Stochastic-Greedy Bandit

In this paper, we consider an infinite horizon average reward Markov Decision Process (MDP). Distinguishing itself from existing works within this context, our approach harnesses the power of the general policy gradient-based algorithm, liberating it from the constraints of assuming a linear MDP structure. We propose a vanilla policy gradient-based algorithm and show its global convergence property. We then prove that the proposed algorithm has O(T^3/4) regret. Remarkably, this paper marks a pioneering effort by presenting the first exploration into regret bound computation for the general parameterized policy gradient algorithm in the context of average reward scenarios.

Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes

We consider the problem of constrained Markov decision process (CMDP) in continuous state-actions spaces where the goal is to maximize the expected cumulative reward subject to some constraints. We propose a novel Conservative Natural Policy Gradient Primal-Dual Algorithm (C-NPG-PD) to achieve zero constraint violation while achieving state of the art convergence results for the objective value function. For general policy parametrization, we prove convergence of value function to global optimal upto an approximation error due to restricted policy class. We even improve the sample complexity of existing constrained NPG-PD algorithm \cite{Ding2020} from 1/eps^6 to 1/eps^4. To the best of our knowledge, this is the first work to establish zero constraint violation with Natural policy gradient style algorithms for infinite horizon discounted CMDPs. We demonstrate the merits of proposed algorithm via experimental evaluations.

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm


Multi-Objective Reinforcement Learning (MORL) setup naturally arises in many places where an agent optimizes multiple objectives. We consider the problem of MORL where multiple objectives are combined using a non-linear scalarization. We combine the vector objectives with a concave scalarization function and maximize this scalar objective. To work with the non-linear scalarization, in this paper, we propose a solution using steady-state occupancy measures and long-term average rewards. We show that when the scalarization function is element-wise increasing, the optimal policy for the scalarization is also Pareto optimal. To maximize the scalarized objective, we propose a model-based posterior sampling algorithm that obtains a regret bound of $\Tilde{O}(KDS\sqrt{A/T})$ for $K$ objectives. Additionally, we propose policy-gradient and actor-critic algorithms for MORL. For the policy gradient actor, we obtain the gradient using chain rule, and we learn different critics for each of the $K$ objectives. Finally, we implement our algorithms on multiple environments including deep-sea treasure, and network scheduling setups to demonstrate that the proposed algorithms can optimize non-linear scalarization of multiple objectives.

Multi-Objective Reinforcement Learning with Non-Linear Scalarization

Reinforcement learning is widely used in applications where one needs to perform sequential decisions while interacting with the environment. The problem becomes more challenging when the decision requirement includes satisfying some safety constraints. The problem is mathematically formulated as constrained Markov decision process (CMDP). In the literature, various algorithms are available to solve CMDP problems in a model-free manner to achieve epsilon-optimal cumulative reward with epsilon feasible policies. An epsilon-feasible policy implies that it suffers from constraint violation. An important question here is whether we can achieve epsilon-optimal cumulative reward with zero constraint violations or not. To achieve that, we advocate the use of a randomized primal-dual approach to solve the CMDP problems and propose a conservative stochastic primal-dual algorithm (CSPDA) which is shown to exhibit O(1/epsilon^2) sample complexity to achieve epsilon-optimal cumulative reward with zero constraint violations. In the prior works, the best available sample complexity for the epsilon-optimal policy with zero constraint violation is O(1/epsilon^5). Hence, the proposed algorithm provides a significant improvement compared to the state of the art.

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach

For remote telesurgery, the bandwidth requirement can be reduced by transferring atomic surgical actions (“surgemes") instead of the low-level kinematic information. However, such a policy requires accurate recognition of these surgemes. Surgeme recognition requires the surgical data for training the classifier. In this paper, we employ transfer learning to reduce the data requirement by transferring knowledge from training task (peg-transfer) to a surgical task (debridement). With different ablations we demonstrate that tranfer learning requires 40% less data than with no-transfer.

Dexterous Skill Transfer between Surgical Procedures for Teleoperated Robotic Surgery

We consider the problem where $M$ agents interact with $M$ identical and independent environments with $S$ states and $A$ actions using reinforcement learning for $T$ rounds. The agents share their data with a central server to minimize their regret. We aim to find an algorithm that allows the agents to minimize the regret with infrequent communication rounds. We provide \NAM\ which runs at each agent and prove that the total cumulative regret of $M$ agents is upper bounded as $\Tilde{O}(DS\sqrt{MAT})$ for a Markov Decision Process with diameter $D$, number of states $S$, and number of actions $A$. The agents synchronize after their visitations to any state-action pair exceeds a certain threshold. Using this, we obtain a bound of $O\left(MSA\log(MT)\right)$ on the total number of communications rounds. Finally, we evaluate the algorithm against multiple environments and demonstrate that the proposed algorithm performs at par with an always communication version of the UCRL2 algorithm, while with significantly lower communication.

Communication Efficient Parallel Reinforcement Learning

We consider the bandit problem of selecting K out of N arms at each time step. The joint reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing among all possible combinations, making the action space large. To simplify the problem, existing works on combinatorial bandits typically assume feedback as a linear function of individual rewards. In this paper, we prove the lower bound for top-K subset selection with bandit feedback with possibly correlated rewards. We present a novel algorithm for the combinatorial setting without using individual arm feedback or requiring linearity of the reward function. Additionally, our algorithm works on correlated rewards of individual arms. Our algorithm, aDaptive Accept RejecT (DART), sequentially finds good arms and eliminates bad arms based on confidence bounds. DART is computationally efficient and uses storage linear in N. Further, DART  achieves a regret bound of Ã•(KâˆšKNT) for a time horizon T, which matches the lower bound in bandit feedback up to a factor of âˆšlog 2NT. When applied to the problem of cross-selling optimization and maximizing the mean of individual rewards, the performance of the proposed algorithm surpasses that of state-of-the-art algorithms. We also show that DART significantly outperforms existing methods for both linear and non-linear joint reward environments.

DART: Adaptive Accept Reject Algorithm for Non-Linear Combinatorial Bandits

AIA Poster Session 2

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

AAAI 2025

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Main Track - Machine Learning

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

AAAI 2024

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

ML: Reinforcement Learning Algorithms 4

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


AAAI 2023

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

**Session Chair:** Felipe Leno da Silva

Oral Session 1A2-2

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

The AAMAS conference series was initiated in 2002 in Bologna, Italy as a joint event comprising the 6th International Conference on Autonomous Agents (AA), the 5th International Conference on Multiagent Systems (ICMAS), and the 9th International Workshop on Agent Theories, Architectures, and Languages (ATAL).

Subsequent AAMAS conferences have been held in Melbourne, Australia (July 2003), New York City, NY, USA (July 2004), Utrecht, The Netherlands (July 2005), Hakodate, Japan (May 2006), Honolulu, Hawaii, USA (May 2007), Estoril, Portugal (May 2008), Budapest, Hungary (May 2009), Toronto, Canada (May 2010), Taipei, Taiwan (May 2011), Valencia, Spain (June 2012), Minnesota, USA (May 2013), Paris, France (May 2014), Istanbul, Turkey (May 2015), Singapore (May 2016), São Paulo (2017) and Stockholm, Sweden (2018), Montreal (May 2019), Auckland (May 2020, Virtual), London (May 2021, Virtual).

A ticket is required to attend this event, please register using the link below:

https://aamas2022-conference.auckland.ac.nz/attending/registration/

Registration Is Required

AAMAS 2022

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

Main_Track

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

Interactive 4A - Applications of Social Robots 3

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. This theme also touches upon people's expectations and perceptions of robots, as well as other social, cognitive and cultural factors that will influence human-robot interactions. We will have a special session/track on this topic, invite targeted submissions and include plenary speakers who are specialist in this area. We sincerely hope that this focus will help enlighten the design-thinking of all of us as we fabricate and program our own various systems.

To access RO-MAN Virtual 2021, [please register here.](https://ro-man2021.org/registration/)

IEEE RO-MAN 2021

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. 

**Session Chair**: Jonas Peters 
**BLOCK II**
<hr> </hr>

Lightning Talks I

lightning talk

The Conference on Uncertainty in Artificial Intelligence (UAI) is one of the premier international conferences on research related to knowledge representation, learning, and reasoning in the presence of uncertainty. It is supported by the [Association for Uncertainty in Artificial Intelligence (AUAI).](https://www.auai.org/)

The 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021) is held fully online. We have an exciting program consisting of keynote talks by [Susan Murphy](https://www.auai.org/uai2021/program?block=A), [Eric Horvitz](https://www.auai.org/uai2021/program?block=B), [Lenka Zdeborová](https://www.auai.org/uai2021/program?block=C), [Judea Pearl](https://www.auai.org/uai2021/program?block=D) and [Ankur Moitra](https://www.auai.org/uai2021/program?block=E), a town hall meeting, peer-reviewed papers, and three workshops. The main conference is single-track and each paper is show-cased with a live component (either a live discussion and Q&A, or a live lightning talk). All papers are also featured in video presentations and in poster sessions in gather.town. The three parallel workshops on Friday allow for smaller meetings on current topics.

The walkthrough video below shows how you can navigate this site and use the different possibilities for interaction: UAIsland2021 on gather.town for posters and social interactions, the mementor platform for virtual mentoring sessions, and the chat and Q&A systems for discussions about talks and posters.

Have a great UAI 2021! 
 
 Cassio de Campos and Marloes Maathuis
 UAI 2021 Program Chairs
 uai2021programchairs@gmail.com

<figure class="video_container">
 <iframe src="https://screencast-o-matic.com/watch/cri0lsViAGK?v=6&ff=1&title=0&controls=1" width=526 height=226 frameborder="0" allowfullscreen="true"> </iframe>
</figure>

A ticket is required to access this conference. Please use the provided link to register for the event.

https://auai.org/uai2021/registration

UAI 2021

The Conference on Uncertainty in Artificial Intelligence (UAI) is one of the premier international conferences on research related to knowledge representation, learning, and reasoning in the presence of uncertainty. It is supported by the [Association for Uncertainty in Artificial Intelligence (AUAI).](https://www.auai.org/)

Vaneet Aggarwal

9

89

Presentations

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment

Combinatorial Stochastic-Greedy Bandit

Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm

Multi-Objective Reinforcement Learning with Non-Linear Scalarization

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach

Dexterous Skill Transfer between Surgical Procedures for Teleoperated Robotic Surgery

Communication Efficient Parallel Reinforcement Learning

DART: Adaptive Accept Reject Algorithm for Non-Linear Combinatorial Bandits

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES