相关论文: Importance of Empirical Sample Complexity Analysis…

Offline reinforcement learning (RL) aims to find an optimal policy for Markov decision processes (MDPs) using a pre-collected dataset. In this work, we revisit the linear programming (LP) reformulation of Markov decision processes for…

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-…

The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral…

In this work, we argue for the importance of an online evaluation budget for a reliable comparison of deep offline RL algorithms. First, we delineate that the online evaluation budget is problem-dependent, where some problems allow for less…

Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap,…

Offline reinforcement learning, which aims at optimizing sequential decision-making strategies with historical data, has been extensively applied in real-life applications. State-Of-The-Art algorithms usually leverage powerful function…

Amazon and other e-commerce sites must employ mechanisms to protect their millions of customers from fraud, such as unauthorized use of credit cards. One such mechanism is order fraud evaluation, where systems evaluate orders for fraud…

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalization performance of new policies. However, this type of…

In recent years, significant progress has been made in multi-objective reinforcement learning (RL) research, which aims to balance multiple objectives by incorporating preferences for each objective. In most existing studies, specific…

We introduce an offline reinforcement learning (RL) algorithm that explicitly clones a behavior policy to constrain value learning. In offline RL, it is often important to prevent a policy from selecting unobserved actions, since the…

We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation.…

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…

Offline reinforcement learning (RL) aims to learn from historical data without requiring (costly) access to the environment. To facilitate offline RL research, we previously introduced NeoRL, which highlighted that datasets from real-world…

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

Offline reinforcement learning (RL) can be used to improve future performance by leveraging historical data. There exist many different algorithms for offline RL, and it is well recognized that these algorithms, and their hyperparameter…

There is a growing interest in using reinforcement learning (RL) to personalize sequences of treatments in digital health to support users in adopting healthier behaviors. Such sequential decision-making problems involve decisions about…

The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be…

Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is…

Reinforcement Learning has received wide interest due to its success in competitive games. Yet, its adoption in everyday applications is limited (e.g. industrial, home, healthcare, etc.). In this paper, we address this limitation by…

We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment.…