Search Results for author:
Found 2 papers, 0 papers with code
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward.
Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards
By analyzing the change in the maximum expected hitting cost, this work presents a formal understanding of the effect of potential-based reward shaping on regret (and sample complexity) in the undiscounted average reward setting.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
