activity
20242026
collaborators

7 papers

cs.LG2026

Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning

Parham Mohammad Panahi, Armin Ashrafi, Haoyu Du +3

Experience replay remains one of the most practical and useful algorithmic tools in the deep reinforcement learning (DRL) toolbox. Aside from the limited success of prioritized rep…

cs.LG2026

Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy

Matthew Vandergrift, Esraa Elelimy, Martha White

One goal in reinforcement learning (RL) research is to understand general-purpose sequential decision-making, using benchmark simulators as a proxy for learning in deployment setti…

cs.LG2026

Gradient Iterated Temporal-Difference Learning

Théo Vincent, Kevin Gerhardt, Yogesh Tripathi +5

Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update…

cs.LG2026

Forager: a lightweight testbed for continual learning with partial observability in RL

Steven Tang, Xinze Xiong, Anna Hakhverdyan +7

In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have…

cs.LG2025

Position: Lifetime tuning is incompatible with continual reinforcement learning

Golnaz Mesbahi, Parham Mohammad Panahi, Olya Mastikhina +3

In continual RL we want agents capable of never-ending learning, and yet our evaluation methodologies do not reflect this. The standard practice in RL is to assume unfettered acces…

cs.LG2025

Fine-Tuning without Performance Degradation

Han Wang, Adam White, Martha White

Fine-tuning policies learned offline remains a major challenge in application domains. Monotonic performance improvement during \emph{fine-tuning} is often challenging, as agents t…