Sham M. Kakade

Publications
Influence

Reinforcement Learning in POMDPs Without Resets

Eyal Even-Dar, S. M. Kakade, Y. Mansour
Computer Science
IJCAI
30 July 2005

We present new algorithms for learning in POMDPs which guarantee that the agent will obtain the optimal average reward in the limit. Expand

Planning in POMDPs Using Multiplicity Automata

Eyal Even-Dar, S. M. Kakade, Y. Mansour
Computer Science, Mathematics
UAI
26 July 2005

We show that POMDPs can be represented by multiplicity automata with no increase in the representation size. Expand

On-line Markov Decision Processes

Eyal Even-Dar, S. M. Kakade, Y. Mansour
2006

We consider an MDP setting in which the reward function is allowed to change during each time step of play (possibly in an adversarial manner), yet the dynamics remain fixed. Similar to the experts… Expand

Handwriting and signature recognition

S. M. Kakade, P. Bartakke
Computer Science
2009

Recommended Authors