Related papers: Hypothesis Network Planned Exploration for Rapid M…

Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during…

Current inference systems for Mixture-of-Experts (MoE) models primarily employ static parallelization strategies. However, these static approaches cannot consistently achieve optimal performance across different inference scenarios, as they…

In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, the accumulated knowledge should be learned in a…

Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network…

Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly to new tasks at…

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

Deep Neural Networks (or DNNs) must constantly cope with distribution changes in the input data when the task of interest or the data collection protocol changes. Retraining a network from scratch to combat this issue poses a significant…

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some…

The goal of meta-reinforcement learning (meta-RL) is to build agents that can quickly learn new tasks by leveraging prior experience on related tasks. Learning a new task often requires both exploring to gather task-relevant information and…

Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward…

We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on contexts, and learn based only on a reward signal from the…

Reward models trained on aggregate preferences often fail to capture individual users' values, but existing adaptation methods such as fine-tuning or long-context conditioning are too costly for real-time personalization. We propose…

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

This work proposes a procedure for designing algorithms for specific adaptive data collection tasks like active learning and pure-exploration multi-armed bandits. Unlike the design of traditional adaptive algorithms that rely on…

We propose RAPid-Learn: Learning to Recover and Plan Again, a hybrid planning and learning method, to tackle the problem of adapting to sudden and unexpected changes in an agent's environment (i.e., novelties). RAPid-Learn is designed to…

Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the…

Reinforcement Learning (RL)-based motion planning has recently shown the potential to outperform traditional approaches from autonomous navigation to robot manipulation. In this work, we focus on a motion planning task for an evasive target…

Meta-reinforcement learning (meta-RL) aims to quickly solve new tasks by leveraging knowledge from prior tasks. However, previous studies often assume a single mode homogeneous task distribution, ignoring possible structured heterogeneity…

Hierarchical reinforcement learning (HRL) helps address large-scale and sparse reward issues in reinforcement learning. In HRL, the policy model has an inner representation structured in levels. With this structure, the reinforcement…