Reinforcement learning with history dependent dynamic contexts
Abstract We introduce Dynamic Contextual Markov Decision Processes (DCMDPs), a novel
reinforcement learning framework for history-dependent environments that generalizes the …
reinforcement learning framework for history-dependent environments that generalizes the …
Batch Ensemble for Variance Dependent Regret in Stochastic Bandits
Efficiently trading off exploration and exploitation is one of the key challenges in online
Reinforcement Learning (RL). Most works achieve this by carefully estimating the model …
Reinforcement Learning (RL). Most works achieve this by carefully estimating the model …
Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics
While popularity bias is recognized to play a crucial role in recommmender (and other
ranking-based) systems, detailed analysis of its impact on collective user welfare has largely …
ranking-based) systems, detailed analysis of its impact on collective user welfare has largely …
" You just can't go around killing people''Explaining Agent Behavior to a Human Terminator
Consider a setting where a pre-trained agent is operating in an environment and a human
operator can decide to temporarily terminate its operation and take-over for some duration of …
operator can decide to temporarily terminate its operation and take-over for some duration of …