Related papers: Lever: Inference-Time Policy Reuse under Support C…
Effective decision making involves flexibly relating past experiences and relevant contextual information to a novel situation. In deep reinforcement learning (RL), the dominant paradigm is for an agent to amortise information that helps…
Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This great promise has motivated a large amount of research that hopes to replicate…
In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL…
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…
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…
Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the…
Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning ability of large language models, yet training remains costly because many rollouts contribute little to optimization, considering the amount of computation…
Navigating fluently around pedestrians is a necessary capability for mobile robots deployed in human environments, such as buildings and homes. While research on social navigation has focused mainly on the scalability with the number of…
Executing workflows on volunteer computing resources where individual tasks may be forced to relinquish their resource for the resource's primary use leads to unpredictability and often significantly increases execution time. Task…
One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…
Reinforcement learning (RL) enables sequential decision-making in complex and high-dimensional environments through interaction with the environment. In most real-world applications, however, a high number of interactions are infeasible. In…
Sample efficiency and performance in the offline setting have emerged as significant challenges of deep reinforcement learning. We introduce Q-Value Weighted Regression (QWR), a simple RL algorithm that excels in these aspects. QWR is an…
Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to be designed by hand.…
Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance…
Recent advances in reinforcement learning with verifiable rewards (RLVR) show that large language models enhance their reasoning abilities when trained with verifiable signals. However, due to reward sparsity, effectiveness depends heavily…
The performance of reinforcement learning depends upon designing an appropriate action space, where the effect of each action is measurable, yet, granular enough to permit flexible behavior. So far, this process involved non-trivial user…
Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…
Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and…
In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such…
Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). However, the inference process of diffusion model can be slow,…