相关论文: Theoretical Barriers in Bellman-Based Reinforcemen…

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…

In recent years, on-policy reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numerous low-…

Reinforcement learning has shown great potential in solving complex tasks when large amounts of data can be generated with little effort. In robotics, one approach to generate training data builds on simulations based on dynamics models…

We consider the problem of Reinforcement Learning for nonlinear stochastic dynamical systems. We show that in the RL setting, there is an inherent ``Curse of Variance" in addition to Bellman's infamous ``Curse of Dimensionality", in…

Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations, but the underlying (''latent'') dynamics are comparatively simple. However, outside of restrictive…

Many traditional algorithms for solving combinatorial optimization problems involve using hand-crafted heuristics that sequentially construct a solution. Such heuristics are designed by domain experts and may often be suboptimal due to the…

Hierarchical reinforcement learning deals with the problem of breaking down large tasks into meaningful sub-tasks. Autonomous discovery of these sub-tasks has remained a challenging problem. We propose a novel method of learning sub-tasks…

Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the…

When faced with a novel scenario, it can be hard to succeed on the first attempt. In these challenging situations, it is important to know how to retry quickly and meaningfully. Retrying behavior can emerge naturally in robots trained on…

We explore a collaborative and cooperative multi-agent reinforcement learning setting where a team of reinforcement learning agents attempt to solve a single cooperative task in a multi-scenario setting. We propose a novel multi-agent…

Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This…

We consider the problem of steering a system with unknown, stochastic dynamics to satisfy a rich, temporally layered task given as a signal temporal logic formula. We represent the system as a Markov decision process in which the states are…

This article is a gentle discussion about the field of reinforcement learning in practice, about opportunities and challenges, touching a broad range of topics, with perspectives and without technical details. The article is based on both…

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…

We prove performance guarantees of two algorithms for approximating $Q^\star$ in batch reinforcement learning. Compared to classical iterative methods such as Fitted Q-Iteration---whose performance loss incurs quadratic dependence on…

Reinforcement Learning (RL) has emerged as a powerful paradigm in Artificial Intelligence (AI), enabling agents to learn optimal behaviors through interactions with their environments. Drawing from the foundations of trial and error, RL…

Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for their simplicity and efficiency, but are consequently…

There are two distinct approaches to solving reinforcement learning problems, namely, searching in value function space and searching in policy space. Temporal difference methods and evolutionary algorithms are well-known examples of these…

Machine Learning requires large amounts of labeled data to fit a model. Many datasets are already publicly available, nevertheless forcing application possibilities of machine learning to the domains of those public datasets. The…

Learning to act from observational data without active environmental interaction is a well-known challenge in Reinforcement Learning (RL). Recent approaches involve constraints on the learned policy or conservative updates, preventing…