Add to ORKGThis paper addresses the problem of decision making in unknown finite Markov Decision Processes (MDPs). The uncertainty about the MDPs is modelled, using a prior distri-bution over a set of candidate MDPs. The performance criterion is the expected sum of discounted rewards collected over an infinite length trajectory. Time constraints are de-fined as follows: (i) an off-line phase with a given time budget, which can be used to ex-ploit the prior distribution and (ii) at each time step of the on-line phase, decisions have to be computed within a given time budget. In this setting, two decision-making strate-gies are compared. Firstly, OPPS, which is a recently proposed meta-learning scheme that mainly exploits the off-line phase to perform t...
We consider the problem of learning to act in partially observable, continuous-state-and-action worl...
The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In th...
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behav...
peer reviewedBayesian Reinforcement Learning (BRL) agents aim to maximise the expected collected rew...
Policy search algorithms have facilitated application of Reinforcement Learning (RL) to dynamic syst...
This dissertation considers a particular aspect of sequential decision making under uncertainty in w...
Markov Decision Processes are a mathematical framework widely used for stochastic optimization and c...
While the Bayesian decision-theoretic framework offers an elegantsolution to the problem of decision...
In this work we consider probabilistic approaches to sequential decision making. The ultimate goal i...
Abstract The problem of reinforcement learning in a non-Markov environment isexplored using a dynami...
This thesis presents research contributions in the study field of Bayesian Reinforcement Learning — ...
In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the col- lected rewards...
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behav...
Effectively leveraging model structure in reinforcement learning is a difficult task, but failure to...
Reinforcement Learning (RL) in either fully or partially observable domains usually poses a requirem...
We consider the problem of learning to act in partially observable, continuous-state-and-action worl...
The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In th...
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behav...
peer reviewedBayesian Reinforcement Learning (BRL) agents aim to maximise the expected collected rew...
Policy search algorithms have facilitated application of Reinforcement Learning (RL) to dynamic syst...
This dissertation considers a particular aspect of sequential decision making under uncertainty in w...
Markov Decision Processes are a mathematical framework widely used for stochastic optimization and c...
While the Bayesian decision-theoretic framework offers an elegantsolution to the problem of decision...
In this work we consider probabilistic approaches to sequential decision making. The ultimate goal i...
Abstract The problem of reinforcement learning in a non-Markov environment isexplored using a dynami...
This thesis presents research contributions in the study field of Bayesian Reinforcement Learning — ...
In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the col- lected rewards...
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behav...
Effectively leveraging model structure in reinforcement learning is a difficult task, but failure to...
Reinforcement Learning (RL) in either fully or partially observable domains usually poses a requirem...
We consider the problem of learning to act in partially observable, continuous-state-and-action worl...
The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In th...
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behav...