Related papers: A Reinforcement Learning Environment for Mathemati…
A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…
Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models. Rationale identification has improved the generalizability and interpretability of neural networks on vision and…
Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data. Existing synthesis methods largely rely on transforming…
We present a method for generating training data for reinforcement learning with verifiable rewards to improve small open-weights language models on mathematical tasks. Existing data generation approaches rely on open-loop pipelines and…
Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…
There has been a recent surge in interest in the application of artificial intelligence to automated trading. Reinforcement learning has been applied to single- and multi-instrument use cases, such as market making or portfolio management.…
Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process. However, through extensive experiments, we find out that the learned policy…
Supervised approaches for text summarisation suffer from the problem of mismatch between the target labels/scores of individual sentences and the evaluation score of the final summary. Reinforcement learning can solve this problem by…
OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…
The problem of retrosynthetic planning can be framed as one player game, in which the chemist (or a computer program) works backwards from a molecular target to simpler starting materials though a series of choices regarding which reactions…
This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence…
Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable way is one of the current fundamental challenges in machine…
Assigning resources in business processes execution is a repetitive task that can be effectively automated. However, different automation methods may give varying results that may not be optimal. Proper resource allocation is crucial as it…
Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR…
Abstract symbolic reasoning, as required in domains such as mathematics and logic, is a key component of human intelligence. Solvers for these domains have important applications, especially to computer-assisted education. But learning to…
We propose a learning architecture that allows symbolic control and guidance in reinforcement learning with deep neural networks. We introduce SymDQN, a novel modular approach that augments the existing Dueling Deep Q-Networks (DuelDQN)…
This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target…
Advances in reinforcement learning research have demonstrated the ways in which different agent-based models can learn how to optimally perform a task within a given environment. Reinforcement leaning solves unsupervised problems where…
We study the problem of experiment design to learn causal structures from interventional data. We consider an active learning setting in which the experimenter decides to intervene on one of the variables in the system in each step and uses…
Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on…