Related papers: Navigation with QPHIL: Quantizing Planner for Hier…

Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tasks involving sparse rewards. Existing goal-conditioned and…

Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods face two fundamental challenges: (i) non-stationarity caused by the evolving…

Deep reinforcement learning algorithms have succeeded in several challenging domains. Classic Online RL job schedulers can learn efficient scheduling strategies but often takes thousands of timesteps to explore the environment and adapt…

Large language models distill broad knowledge from text corpora. However, they can be inconsistent when it comes to completing user specified tasks. This issue can be addressed by finetuning such models via supervised learning on curated…

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task. While this problem has been well investigated, the related problem of {\em online} IRL---where the…

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and online or offline. Broad classification schemes such as…

Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inadequate for capturing the compositional structure of tasks…

One of the main challenges in reinforcement learning (RL) is that the agent has to make decisions that would influence the future performance without having complete knowledge of the environment. Dynamically adjusting the level of epistemic…

Diffusion-based generative methods have shown promising potential for modeling trajectories from offline reinforcement learning (RL) datasets, and hierarchical diffusion has been introduced to mitigate variance accumulation and…

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

Two central paradigms have emerged in the reinforcement learning (RL) community: online RL and offline RL. In the online RL setting, the agent has no prior knowledge of the environment, and must interact with it in order to find an…

Standard reinforcement learning algorithms with a single policy perform poorly on tasks in complex environments involving sparse rewards, diverse behaviors, or long-term planning. This led to the study of algorithms that incorporate…

In this paper, we propose a fast reinforcement learning (RL) control algorithm that enables online control of large-scale networked dynamic systems. RL is an effective way of designing model-free linear quadratic regulator (LQR) controllers…

Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation…

Deriving a good variable selection strategy in branch-and-bound is essential for the efficiency of modern mixed-integer programming (MIP) solvers. With MIP branching data collected during the previous solution process, learning to branch…

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…

Hierarchical Reinforcement Learning (HRL) agents have the potential to demonstrate appealing capabilities such as planning and exploration with abstraction, transfer, and skill reuse. Recent successes with HRL across different domains…

Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle…

Autonomous off-road navigation requires robots to estimate terrain traversability from onboard sensors and plan motion accordingly. Conventional approaches typically rely on sampling-based planners such as MPPI to generate short-term…