Related papers: Generalisation in Multitask Fitted Q-Iteration and…
The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors,…
In deep Reinforcement Learning (RL), value functions are typically approximated using deep neural networks and trained via mean squared error regression objectives to fit the true value functions. Recent research has proposed an alternative…
Offline reinforcement learning (RL) aims to learn a policy from a static dataset without further interactions with the environment. Collecting sufficiently large datasets for offline RL is exhausting since this data collection requires…
The benefit of multi-task learning over single-task learning relies on the ability to use relations across tasks to improve performance on any single task. While sharing representations is an important mechanism to share information across…
To leverage the power of big data from source tasks and overcome the scarcity of the target task samples, representation learning based on multi-task pretraining has become a standard approach in many applications. However, up until now,…
Q-functions are widely used in discrete-time learning and control to model future costs arising from a given control policy, when the initial state and input are given. Although some of their properties are understood, Q-functions…
When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this…
Multitask learning assumes that models capable of learning from multiple tasks can achieve better quality and efficiency via knowledge transfer, a key feature of human learning. Though, state of the art ML models rely on high customization…
Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide formal performance guarantees, which are indispensable when…
This paper presents a novel approach to generalizing robot manipulation skills by combining a sampling-based task-and-motion planner with an offline reinforcement learning algorithm. Starting with a small library of scripted primitive…
Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned…
Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all states. However, due…
This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…
We show that the popular reinforcement learning (RL) strategy of estimating the state-action value (Q-function) by minimizing the mean squared Bellman error leads to a regression problem with confounding, the inputs and output noise being…
We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an…
Most contemporary multi-task learning methods assume linear models. This setting is considered shallow in the era of deep learning. In this paper, we present a new deep multi-task representation learning framework that learns cross-task…
The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…
In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suffer from a limited…
Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…
Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online…