相关论文: Generalizing Across Multi-Objective Reward Functio…

Inverse Reinforcement Learning addresses the problem of inferring an expert's reward function from demonstrations. However, in many applications, we not only have access to the expert's near-optimal behavior, but we also observe part of her…

Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area…

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…

Reinforcement learning agents learn by encouraging behaviours which maximize their total reward, usually provided by the environment. In many environments, however, the reward is provided after a series of actions rather than each single…

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

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…

Deep reinforcement learning algorithms have shown an impressive ability to learn complex control policies in high-dimensional tasks. However, despite the ever-increasing performance on popular benchmarks, policies learned by deep…

Deep Reinforcement Learning (DRL) has shown its promising capabilities to learn optimal policies directly from trial and error. However, learning can be hindered if the goal of the learning, defined by the reward function, is "not optimal".…

Incorporating high-level knowledge is an effective way to expedite reinforcement learning (RL), especially for complex tasks with sparse rewards. We investigate an RL problem where the high-level knowledge is in the form of reward machines,…

Dealing with sparse rewards is a long-standing challenge in reinforcement learning (RL). Hindsight Experience Replay (HER) addresses this problem by reusing failed trajectories for one goal as successful trajectories for another. This…

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…

In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and trained on and have been extensively studied in the RL…

To date, distributional reinforcement learning (distributional RL) methods have exclusively focused on the discounted setting, where an agent aims to optimize a discounted sum of rewards over time. In this work, we extend distributional RL…

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…

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants…

We study the problem of reinforcement learning for a task encoded by a reward machine. The task is defined over a set of properties in the environment, called atomic propositions, and represented by Boolean variables. One unrealistic…

Reinforcement learning (RL) enables agents to take decision based on a reward function. However, in the process of learning, the choice of values for learning algorithm parameters can significantly impact the overall learning process. In…

Machine learning algorithms learn to solve a task, but are unable to improve their ability to learn. Meta-learning methods learn about machine learning algorithms and improve them so that they learn more quickly. However, existing…