Canada

In application domains requiring mission-critical decision making, such as finance and robotics, the optimal policy derived by reinforcement learning (RL) often hinges on a preference for risk management. Yet, the dynamic nature of risk measures poses considerable challenges to achieving generalization and adaptation of risk-sensitive policies in the context of RL. In this paper, we propose a risk-conditioned RL model that enables rapid policy adaptation to varying risk measures via a unified risk representation, the Weighted Value-at-Risk (WV@R). To sample risk measures that avoid undue optimism, we construct a risk proposal network employing a conditional adversarial auto-encoder and a normalizing flow. This network establishes coherent representations for risk measures, preserving the continuity in terms of the Wasserstein distance on the risk measures. The normalizing flow is used to support non-crossing quantile regression that obtains valid samples for risk measures, and it is also applied to the agent’s critic to ascertain the preservation of monotonicity in quantile estimations. Through experiments with locomotion, finance, and self-driving scenarios, we show that our model is capable of adapting to a range of risk measures, achieving comparable performance to the baseline models individually trained for each measure. Our model often outperforms the baselines, especially in the cases when exploration is required during training but risk-aversion is favored during evaluation.

AAAI 2024

Risk-Conditioned Reinforcement Learning: A Generalized Approach for Adapting to Varying Risk Measures

ru: applications

ru: sequential decision making

ru: uncertainty representations

ml: reinforcement learning algorithms

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.<br><br><br><br>

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

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. 

Instruction-following is particularly crucial for large language models (LLMs) to support diverse user requests. While existing work has made progress in aligning LLMs with human preferences, evaluating their capabilities on instruction-following remains a challenge due to complexity and diversity of real-world user instructions. While existing evaluation methods focus on general skills, they suffer from two main shortcomings, i.e., lack of fine-grained task-level evaluation and reliance on singular instruction expression. To address these problems, this paper introduces DINGO, a fine-grained and diverse instruction-following evaluation dataset that has two main advantages: (1) DINGO is based on a manual-annotated, fine-grained and multi-level category tree with 140 nodes derived from real-world user requests; (2) DINGO includes diverse instructions, generated by both GPT-4 and human experts. Through extensive experiments, we demonstrate that DINGO can not only provide more challenging and comprehensive evaluation for LLMs, but also provide task-level fine-grained directions to further improve LLMs.

DINGO: Towards Diverse and Fine-Grained Instruction-Following Evaluation

Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning. In the context of confident learning, low self-confidence usually indicates potential label errors; however, this is not always the case. Instances, particularly those from underrepresented groups, might exhibit low confidence scores for reasons other than labeling errors. To address this limitation, our approach employs truncation of the confidence score and extends the confidence interval of the probabilistic threshold. Additionally, we incorporate with co-teaching paradigm for providing a more robust and reliable selection of fair instances and effectively mitigating the adverse effects of biased labels. Through extensive experimentation and evaluation of various datasets, we demonstrate the efficacy of our approach in promoting fairness and reducing the impact of label bias in machine learning models.

Mitigating Label Bias in Machine Learning: Fairness through Confident Learning

Bioinformatics has always been a prolific domain for generating complex satisfiability and optimization problems. For instance, the synthesis of multi-scale models of biological networks has recently been associated with the resolution of optimization problems mixing Boolean logic and universally quantified linear constraints (OPT+qLP), which can be benchmarked on real-world models. In this paper, we introduce a Counter-Example-Guided Abstraction Refinement (CEGAR) to solve such problems efficiently. Our CEGAR exploits monotone properties inherent to linear optimization in order to generalize counter-examples of Boolean relaxations. We implemented our approach by extending Answer Set Programming (ASP) solver Clingo with a quantified linear constraints propagator. Our prototype enables exploiting independence of sub-formulas to further exploit the generalization of counter-examples. We evaluate the impact of refinement and partitioning on two sets of OPT+qLP problems inspired by system biology. Additionally, we conducted a comparison with the state-of-the-art ASP solver Clingo[lpx] that handles non-quantified linear constraints, showing the advantage of our CEGAR approach for solving large problems.

CEGAR-Based Approach for Solving Combinatorial Optimization Modulo Quantified Linear Arithmetics Problems

The effectiveness of advertising in e-commerce largely depends on the ability of merchants to bid on and win impressions for their targeted users. The bidding procedure is highly complex due to various factors such as market competition, user behavior, and the diverse objectives of advertisers. In this paper we consider the problem at the level of user timelines instead of individual bid requests, manipulating full policies (i.e. pre-defined bidding strategies) and not bid values. In order to optimally allocate policies to users, typical multiple treatments allocation methods solve knapsack-like problems which aim at maximizing an expected value under constraints. In the specific context of online advertising, we argue that optimizing for the probability of success is a more suited objective than expected value maximization, and we introduce the SuccessProbaMax algorithm that aims at finding the policy allocation which is the most likely to outperform a fixed reference policy. Finally, we conduct comprehensive experiments both on synthetic and real-world data to evaluate its performance. The results demonstrate that our proposed algorithm outperforms conventional expected-value maximization algorithms in terms of success rate.

Maximizing the Success Probability of Policy Allocations in Online Systems

In this paper, we present our finding that prepending a Task-Agnostic Prefix Prompt (TAPP) to the input improves the instruction-following ability of various Large Language Models (LLMs) during inference. TAPP is different from canonical prompts for LLMs in that it is a fixed prompt prepended to the beginning of every input regardless of the target task for zero-shot generalization. We observe that both base LLMs (i.e. not fine-tuned to follow instructions) and instruction-tuned models benefit from TAPP, resulting in 34.58% and 12.26% improvement on average, respectively. This implies that the instruction-following ability of LLMs can be improved during inference time with a fixed prompt constructed with simple heuristics. We hypothesize that TAPP assists language models to better estimate the output distribution by focusing more on the instruction of the target task during inference. In other words, such ability does not seem to be sufficiently activated in not only base LLMs but also many instruction-fine-tuned LLMs.

Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following

Document-level relation extraction (DocRE) poses the challenge of identifying relationships between entities within a document. Existing approaches rely on logical reasoning or contextual cues from entities. This paper reframes document-level RE as link prediction over a Knowledge Graph (KG) with distinct benefits: 1) Our approach amalgamates entity context and document-derived logical reasoning, enhancing link prediction quality. 2) Predicted links between entities offer interpretability, elucidating employed reasoning. 
We evaluate our approach on benchmark datasets - DocRED, ReDocRED, and DWIE. The results indicate that our proposed method outperforms the state-of-the-art models and suggests that incorporating context-based Knowledge Graph link prediction techniques can enhance the performance of document-level relation extraction models. The code and the models are available at \url{https://anonymous.4open.science/r/DocRE-CED1/}.

Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction

Recent techniques based on Mean Field Games (MFGs) allow the scalable analysis of multi-player games with many similar, rational agents. However, standard MFGs remain limited to homogeneous players that weakly influence each other, and cannot model major players that strongly influence other players, severely limiting the class of problems that can be handled. We propose a novel discrete time version of major-minor MFGs (M3FGs), along with a learning algorithm based on fictitious play and partitioning the probability simplex. Importantly, M3FGs generalize MFGs with common noise and can handle not only random exogeneous environment states but also major players. A key challenge is that the mean field is stochastic and not deterministic as in standard MFGs. Our theoretical investigation verifies both the M3FG model and its algorithmic solution, showing firstly the well-posedness of the M3FG model starting from a finite game of interest, and secondly convergence and approximation guarantees of the fictitious play algorithm. Then, we empirically verify the obtained theoretical results, ablating some of the theoretical assumptions made, and show successful equilibrium learning in three example problems. Overall, we establish a learning framework for a novel and broad class of tractable games.

Learning Discrete-Time Major-Minor Mean Field Games | VIDEO

We address the problem of building and evaluating a computational system whose primary objective is creativity. We illustrate seven characteristics for computational creativity in the context of a system that autonomously composes Western lyrical music. We conduct an external evaluation of the system in which respondents rated the system with regard to each characteristic as well as with regard to overall creativity. Average scores for overall creativity exceeded the ratings for any single characteristic, suggesting that creativity may be an emergent property and that unique research opportunities exist for building CC systems whose design attempts to comprehend all known characteristics of creativity.

Operationalizing Essential Characteristics of Creativity in a Computational System for Music Composition

The literature on game-theoretic equilibrium finding is mainly focused on single-games or their repeated variations. However, there are natural examples where similar versions of a game occur, which go beyond repeated games, such as playing poker with different public cards, or trading on stock markets with
correlated assets. As these games are similar, their equilibrium strategies share similarity as well. Based on this observation, we investigate a way to accelerate equilibrium finding on a distribution over games. We present a novel approach: the
“learning not to regret” framework, enabling us to meta-learn a regret minimizer tailored for a specific distribution. Our key contribution, Neural Predictive Regret Matching (NPRM), offers a method to minimize regret on any game and is uniquely
meta-learned to converge rapidly for the chosen distribution of games. The practicality of NPRM is demonstrated through experiments in river poker games. The results reveal that our meta-learned algorithms provide an improvement by an order of magnitude on the distribution, compared to the variant without meta-learning.

Learning Not to Regret

Social summarization aims to provide summaries for a large number of social texts (called posts)  about a single topic. To extract a summary, both  the representation of post and summary selection method are crucial. Previous methods introduce social relation to enhance post embedding to mitigate the sparse representation due to its brief and informal expression. However, they ignore that there are multiple relations between posts. Besides, existing graph-based centrality calculation approaches tend to select posts from one aspect. This leads to facet bias especially when there are multiple viewpoints. In this paper, we propose a model named MultiSum to improve social summarization. Specifically, 1) We use graph convolutional networks to fuse text content with social and semantic relations to improve post representation; 2) The similarity between the summary and all aspects is incorporated into the centrality score during the selection phase, encouraging the model to pay attention to different facets. Experimental results on English and Chinese corpora support the effectiveness of this model. Furthermore, external evaluations by human experts and large language models demonstrate the validity of MultiSum in facet coverage and redundancy reduction.

Risk-Conditioned Reinforcement Learning: A Generalized Approach for Adapting to Varying Risk Measures

Downloads

Next from AAAI 2024

DINGO: Towards Diverse and Fine-Grained Instruction-Following Evaluation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES