Goto

Collaborating Authors

 Ronan Fruit


Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs

Neural Information Processing Systems

The exploration bonus is an effective approach to manage the explorationexploitation trade-off in Markov Decision Processes (MDPs). While it has been analyzed in infinite-horizon discounted and finite-horizon problems, we focus on designing and analysing the exploration bonus in the more challenging infinitehorizon undiscounted setting.


Regret Bounds for Learning State Representations in Reinforcement Learning

Neural Information Processing Systems

We consider the problem of online reinforcement learning when several state representations (mapping histories to a discrete state space) are available to the learning agent. At least one of these representations is assumed to induce a Markov decision process (MDP), and the performance of the agent is measured in terms of cumulative regret against the optimal policy giving the highest average reward in this MDP representation.


Regret Bounds for Learning State Representations in Reinforcement Learning

Neural Information Processing Systems

We consider the problem of online reinforcement learning when several state representations (mapping histories to a discrete state space) are available to the learning agent. At least one of these representations is assumed to induce a Markov decision process (MDP), and the performance of the agent is measured in terms of cumulative regret against the optimal policy giving the highest average reward in this MDP representation.