
Nearoptimal Reinforcement Learning in Factored MDPs
Any reinforcement learning algorithm that applies to all Markov decision...
read it

Active Reinforcement Learning with MonteCarlo Tree Search
Active Reinforcement Learning (ARL) is a twist on RL where the agent obs...
read it

Efficient BayesAdaptive Reinforcement Learning using SampleBased Search
Bayesian modelbased reinforcement learning is a formally elegant approa...
read it

Robust and Adaptive Planning under Model Uncertainty
Planning under model uncertainty is a fundamental problem across many ap...
read it

Generalized Mean Estimation in MonteCarlo Tree Search
We consider MonteCarlo Tree Search (MCTS) applied to Markov Decision Pr...
read it

RUDDER: Return Decomposition for Delayed Rewards
We propose a novel reinforcement learning approach for finite Markov dec...
read it

Vulcan: A Monte Carlo Algorithm for Large Chance Constrained MDPs with Risk Bounding Functions
Chance Constrained Markov Decision Processes maximize reward subject to ...
read it
Learning is planning: near Bayesoptimal reinforcement learning via MonteCarlo tree search
Bayesoptimal behavior, while welldefined, is often difficult to achieve. Recent advances in the use of MonteCarlo tree search (MCTS) have shown that it is possible to act nearoptimally in Markov Decision Processes (MDPs) with very large or infinite state spaces. Bayesoptimal behavior in an unknown MDP is equivalent to optimal behavior in the known beliefspace MDP, although the size of this beliefspace MDP grows exponentially with the amount of history retained, and is potentially infinite. We show how an agent can use one particular MCTS algorithm, Forward Search Sparse Sampling (FSSS), in an efficient way to act nearly Bayesoptimally for all but a polynomial number of steps, assuming that FSSS can be used to act efficiently in any possible underlying MDP.
READ FULL TEXT
Comments
There are no comments yet.