7 papers
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…
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…
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…
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…
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…
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…