2 papers
cs.LG2026
Task diversity produces systematic transfer but inhibits continual reinforcement learning
Purab Seth, Neil Shah, Kunal Jha +3
Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions change. Training an agent on m…
cs.AI2024
Predictive representations: building blocks of intelligence
Wilka Carvalho, Momchil S. Tomov, William de Cothi +2
Adaptive behavior often requires predicting future events. The theory of reinforcement learning prescribes what kinds of predictive representations are useful and how to compute th…