Related papers: Backward explanations via redefinition of predicat…

The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which…

Deep reinforcement learning (DRL) algorithms have achieved great success on sequential decision-making problems, yet is criticized for the lack of data-efficiency and explainability. Especially, explainability of subtasks is critical in…

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

Deep Reinforcement Learning (RL) involves the use of Deep Neural Networks (DNNs) to make sequential decisions in order to maximize reward. For many tasks the resulting sequence of actions produced by a Deep RL policy can be long and…

A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem. Hyperparameter tuning often…

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated…

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning (RL). Hierarchical reinforcement learning (HRL) addresses this by decomposing tasks into more manageable sub-tasks, but the automatic…

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Explanation is a key component for the adoption of reinforcement learning (RL) in many real-world decision-making problems. In the literature, the explanation is often provided by saliency attribution to the features of the RL agent's…

The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations…

This paper deals with robotic lever control using Explainable Deep Reinforcement Learning. First, we train a policy by using the Deep Deterministic Policy Gradient algorithm and the Hindsight Experience Replay technique, where the goal is…

Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…

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…

Action advising is a knowledge transfer technique for reinforcement learning based on the teacher-student paradigm. An expert teacher provides advice to a student during training in order to improve the student's sample efficiency and…

Reconstructing past events requires reasoning across long time horizons. To figure out what happened, we need to use our prior knowledge about the world and human behavior and draw inferences from various sources of evidence including…

Attribution methods compute importance scores for input features to explain model predictions. However, assessing the faithfulness of these methods remains challenging due to the absence of attribution ground truth to model predictions. In…

As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a…

Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts `RL as inference' and suggests a…

Value estimation is a critical component of the reinforcement learning (RL) paradigm. The question of how to effectively learn value predictors from data is one of the major problems studied by the RL community, and different approaches…