相关论文: Policy-Value Alignment and Robustness in Search-ba…

Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 games. We identify three key challenges…

As artificial intelligence becomes increasingly intelligent---in some cases, achieving superhuman performance---there is growing potential for humans to learn from and collaborate with algorithms. However, the ways in which AI systems…

Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to faithfully follow language. When presented with instructions that lack strong scene-specific supervision, VLAs…

Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on planning with predefined options or learned options through expert…

Recently, reinforcement learning has achieved remarkable results in various domains, including robotics, games, natural language processing, and finance. In the financial domain, this approach has been applied to tasks such as portfolio…

As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objective in trustworthy AI. This challenge becomes even more…

We introduce a universal policy wrapper for reinforcement learning agents that ensures formal goal-reaching guarantees. In contrast to standard reinforcement learning algorithms that excel in performance but lack rigorous safety assurances,…

Handling missing values in training datasets for constructing learning models or extracting useful information is considered to be an important research task in data mining and knowledge discovery in databases. In recent years, lot of…

In 2019, Google DeepMind released MuZero, a model-based reinforcement learning method that achieves strong results in perfect-information games by combining learned dynamics models with Monte Carlo Tree Search (MCTS). However, comparatively…

Vision-Language-Action (VLA) models have emerged as a promising framework that unifies perception, reasoning, and control for robot manipulation by adapting pretrained vision-language models (VLMs) to action prediction. However, VLM-derived…

One of the main challenges in model-based reinforcement learning (RL) is to decide which aspects of the environment should be modeled. The value-equivalence (VE) principle proposes a simple answer to this question: a model should capture…

Multi-agent reinforcement learning (MARL) algorithms often struggle to find strategies close to Pareto optimal Nash Equilibrium, owing largely to the lack of efficient exploration. The problem is exacerbated in sparse-reward settings,…

Behavioural characterizations (BCs) of decision-making agents, or their policies, are used to study outcomes of training algorithms and as part of the algorithms themselves to encourage unique policies, match expert policy or restrict…

While transformers have gained recognition as a versatile tool for artificial intelligence (AI), an unexplored challenge arises in the context of chess - a classical AI benchmark. Here, incorporating Vision Transformers (ViTs) into…

Vision-Language-Action (VLA) models achieve strong performance in robotic manipulation by leveraging pre-trained vision-language backbones. However, in downstream robotic settings, they are typically fine-tuned with limited data, leading to…

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world…

Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy termed "value-action gap." In this work, we argue that this gap persists even under…

Deep Reinforcement Learning reaches a superhuman level of play in many complete information games. The state of the art algorithm for learning with zero knowledge is AlphaZero. We take another approach, Ath\'enan, which uses a different,…

Prior Vision-Language-Action (VLA) models are typically trained on teleoperated successful demonstrations, while discarding numerous failed attempts that occur naturally during data collection. However, these failures encode where and how…

We study repeated multi-player vector-valued games in which a player observes a payoff vector each round and evaluates outcomes through linear scalarizations of those vectors. Different from most prior works, the choice of scalarization is…