Related papers: Variable-Agnostic Causal Exploration for Reinforce…
Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., complex travel planning). Due to the…
Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined…
Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on…
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning…
Understanding the behavior of deep reinforcement learning (DRL) agents -particularly as task and agent sophistication increase- requires more than simple comparison of reward curves, yet standard methods for behavioral analysis remain…
In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the…
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of…
Dealing with non-stationarity in environments (e.g., in the transition dynamics) and objectives (e.g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). While most…
A topic of great current interest is Causal Representation Learning (CRL), whose goal is to learn a causal model for hidden features in a data-driven manner. Unfortunately, CRL is severely ill-posed since it is a combination of the two…
We propose an explainable reinforcement learning (XRL) framework that analyzes an agent's history of interaction with the environment to extract interestingness elements that help explain its behavior. The framework relies on data readily…
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 (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the…
Continual learning (CL) enables the development of models and agents that learn from a sequence of tasks while addressing the limitations of standard deep learning approaches, such as catastrophic forgetting. In this work, we investigate…
Characterizing aleatoric and epistemic uncertainty on the predicted rewards can help in building reliable reinforcement learning (RL) systems. Aleatoric uncertainty results from the irreducible environment stochasticity leading to…
An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in tabular settings. However, in non-tabular settings that…
The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly reflect model performance, so we trained evaluation models to…
To increase autonomy in reinforcement learning, agents need to learn useful behaviours without reliance on manually designed reward functions. To that end, skill discovery methods have been used to learn the intrinsic options available to…
Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and…
In-Context Reinforcement Learning (ICRL) has emerged as a promising paradigm for developing agents that can rapidly adapt to new tasks by leveraging past experiences as context, without updating their parameters. Recent approaches train…
Efficient and effective exploration in continuous space is a central problem in applying reinforcement learning (RL) to autonomous driving. Skills learned from expert demonstrations or designed for specific tasks can benefit the…