7 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…
Rethinking the Design of Reinforcement Learning-Based Deep Research Agents
Yi Wan, Jiuqi Wang, Liam Li +3
Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer comp…
Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes
Ethan Blaser, Jiuqi Wang, Shangtong Zhang
The average reward is a fundamental performance metric in reinforcement learning (RL) focusing on the long-run performance of an agent. Differential temporal difference (TD) learni…
Towards Provable Emergence of In-Context Reinforcement Learning
Jiuqi Wang, Rohan Chandra, Shangtong Zhang
Typically, a modern reinforcement learning (RL) agent solves a task by updating its neural network parameters to adapt its policy to the task. Recently, it has been observed that s…
Experience Replay Addresses Loss of Plasticity in Continual Learning
Jiuqi Wang, Rohan Chandra, Shangtong Zhang
Loss of plasticity is one of the main challenges in continual learning with deep neural networks, where neural networks trained via backpropagation gradually lose their ability to…