Related papers: SPICE: Self-Play In Corpus Environments Improves R…

Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample…

Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete…

Recent techniques in Question Answering (QA) have gained remarkable performance improvement with some QA models even surpassed human performance. However, the ability of these models in truly understanding the language still remains dubious…

Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (Generating Rewards As…

Visual learning often occurs in a specific context, where an agent acquires skills through exploration and tracking of its location in a consistent environment. The historical spatial context of the agent provides a similarity signal for…

Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and…

In-context learning is a promising approach for online policy learning of offline reinforcement learning (RL) methods, which can be achieved at inference time without gradient optimization. However, this method is hindered by significant…

Large language model based agents are increasingly deployed in complex, tool augmented environments. While reinforcement learning provides a principled mechanism for such agents to improve through interaction, its effectiveness critically…

This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. We…

Robotic manipulation in unstructured environments requires reliable execution under diverse conditions, yet many state-of-the-art systems still struggle with high-dimensional action spaces, sparse rewards, and slow generalization beyond…

Evaluating the capabilities and risks of foundation models is paramount, yet current methods demand extensive domain expertise, hindering their scalability as these models rapidly evolve. We introduce SKATE: a novel evaluation framework in…

Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio. Due to their adaptiveness in iterative refinement, they provide a strong potential for achieving better non-autoregressive…

Large language models (LLMs) have demonstrated considerable reasoning abilities in various tasks such as mathematics and coding. However, recent studies indicate that even the best models lack true comprehension of their reasoning…

Nash equilibrium (NE) is a widely adopted solution concept in game theory due to its stability property. However, we observe that the NE strategy might not always yield the best results, especially against opponents who do not adhere to NE…

Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered…

Curriculum learning helps language models tackle complex reasoning by gradually increasing task difficulty. However, it often fails to generate consistent step-by-step reasoning, especially in multilingual and low-resource settings where…

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…

Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-supervised reinforcement learning agent that tackles both…

We convert the DeepMind Mathematics Dataset into a reinforcement learning environment by interpreting it as a program synthesis problem. Each action taken in the environment adds an operator or an input into a discrete compute graph. Graphs…

Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for…