Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Indian Institute of Science, Universitat Pompeu Fabra, Univ. Lille, Inria, CNRS-CRIStAL, Centrale Lille
1
0
2
Average-reward option Q-learning achieves $\tilde{O}(1/\text{iterations})$ convergence, unlocking continual RL tasks previously intractable for option-based methods.