5 papers
Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
Jiuqi Wang, Jayanth Srinivasa, Claire Chen +3
Deep continual learning requires models to adapt to new tasks without retraining from scratch. However, neural networks can lose their ability to adapt to new tasks after training…
Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features
Jiuqi Wang, Shangtong Zhang
Temporal difference (TD) learning with linear function approximation (linear TD) is a classic and powerful prediction algorithm in reinforcement learning. While it is well-understo…
Asymptotic and Finite Sample Analysis of Nonexpansive Stochastic Approximations with Markovian Noise
Ethan Blaser, Shangtong Zhang
Stochastic approximation is a powerful class of algorithms with celebrated success. However, a large body of previous analysis focuses on stochastic approximations driven by contra…
Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning
Jiuqi Wang, Ethan Blaser, Hadi Daneshmand +1
Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, rece…
A Survey of In-Context Reinforcement Learning
Amir Moeini, Jiuqi Wang, Jacob Beck +4
Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new…