Related papers: Causal Reinforcement Learning for Complex Card Gam…

Large language models (LLMs) have revolutionized natural language processing (NLP), particularly through Retrieval-Augmented Generation (RAG), which enhances LLM capabilities by integrating external knowledge. However, traditional RAG…

Reinforcement learning is an essential paradigm for solving sequential decision problems under uncertainty. Despite many remarkable achievements in recent decades, applying reinforcement learning methods in the real world remains…

The deployment of multi-agent systems in dynamic, adversarial environments like robotic soccer necessitates real-time decision-making, sophisticated cooperation, and scalable algorithms to avoid the curse of dimensionality. While…

In offline reinforcement learning-based recommender systems (RLRS), learning effective state representations is crucial for capturing user preferences that directly impact long-term rewards. However, raw state representations often contain…

With the fast development of quantitative portfolio optimization in financial engineering, lots of AI-based algorithmic trading strategies have demonstrated promising results, among which reinforcement learning begins to manifest…

A pervasive challenge in Reinforcement Learning (RL) is the "curse of dimensionality" which is the exponential growth in the state-action space when optimizing a high-dimensional target task. The framework of curriculum learning trains the…

A key challenge in multi-agent reinforcement learning (MARL) lies in designing learning signals that effectively promote coordination among agents. Designing such signals requires estimating how one agent's current action affects its…

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…

Observational data are often used to answer causal questions, yet the legitimacy of doing so is often argued to hinge on strong, domain supported assumptions about underlying causal structure with limited guidance on how much domain…

Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding holds promise, instruction-tuned models frequently fail even in…

Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…

Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stems from two key challenges: partial observability and…

Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency and stability of RL…

Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research. Existing methods often focus on state-based metrics, which do not consider the underlying causal structures of…

Causal representation learning (CRL) and traditional representation learning have largely developed along different trajectories. Traditional representation learning has been driven mainly by applications and empirical objectives, whereas…

Over the past few decades, machine learning has been widely used to learn complex tasks. Reinforcement Learning (RL), inspired by human behavior, is a great example, as it involves developing specific behaviours for specific tasks. To…

Most neural models of causality assume static causal graphs, failing to capture the dynamic and sparse nature of physical interactions where causal relationships emerge and dissolve over time. We introduce the Causal Process Framework and…

Recent reinforcement learning approaches, such as outcome-supervised GRPO, have advanced Chain-of-Thought reasoning in large language models (LLMs), yet their adaptation to multimodal LLMs (MLLMs) is unexplored. To address the lack of…

Causal Representation Learning (CRL) aims to uncover the data-generating process and identify the underlying causal variables and relations, whose evaluation remains inherently challenging due to the requirement of known ground-truth causal…

Reinforcement Learning with Verifiable Rewards (RLVR) is commonly based on group sampling to estimate advantages and stabilize policy updates. In practice, computational limits often rule out very large groups, so training proceeds with…