Towards continual reinforcement learning: A review and perspectives
In this article, we aim to provide a literature review of different formulations and approaches
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …
An overview of multi-task learning
As a promising area in machine learning, multi-task learning (MTL) aims to improve the
performance of multiple related learning tasks by leveraging useful information among them …
performance of multiple related learning tasks by leveraging useful information among them …
Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned
on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further …
on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further …
Contrastive learning as goal-conditioned reinforcement learning
In reinforcement learning (RL), it is easier to solve a task if given a good representation.
While deep RL should automatically acquire such good representations, prior work often …
While deep RL should automatically acquire such good representations, prior work often …
Multi-task learning for dense prediction tasks: A survey
S Vandenhende, S Georgoulis… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
With the advent of deep learning, many dense prediction tasks, ie, tasks that produce pixel-
level predictions, have seen significant performance improvements. The typical approach is …
level predictions, have seen significant performance improvements. The typical approach is …
Gradient surgery for multi-task learning
While deep learning and deep reinforcement learning (RL) systems have demonstrated
impressive results in domains such as image classification, game playing, and robotic …
impressive results in domains such as image classification, game playing, and robotic …
Curriculum learning for reinforcement learning domains: A framework and survey
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks
in which the agent has only limited environmental feedback. Despite many advances over …
in which the agent has only limited environmental feedback. Despite many advances over …
Model-based reinforcement learning: A survey
Sequential decision making, commonly formalized as Markov Decision Process (MDP)
optimization, is an important challenge in artificial intelligence. Two key approaches to this …
optimization, is an important challenge in artificial intelligence. Two key approaches to this …
A definition of continual reinforcement learning
In a standard view of the reinforcement learning problem, an agent's goal is to efficiently
identify a policy that maximizes long-term reward. However, this perspective is based on a …
identify a policy that maximizes long-term reward. However, this perspective is based on a …