Add to ORKGWe consider the inverse reinforcement learning problem, that is, the problem of learning from, and then predicting or mimicking a controller based on state/action data. We propose a statistical model for such data, derived from the structure of a Markov decision process. Adopting a Bayesian approach to inference, we show how latent variables of the model can be estimated, and how predictions about actions can be made, in a unified framework. A new Markov chain Monte Carlo (MCMC) sampler is devised for simulation from the posterior distribution. This step includes a parameter expansion step, which is shown to be essential for good convergence properties of the MCMC sampler. As an illustration, the method is applied to learning a human contro...
Bayesian Reinforcement Learning has generated substantial interest recently, as it provides an elega...
Probabilistic inference is at the core of many recent advances in machine learning. Unfortunately, ...
We propose the use of Model Predictive Control (MPC) for controlling systems described by Markov dec...
This work addresses the problem of estimating the optimal value function in a Markov Decision Proces...
This work addresses the problem of estimating the optimal value function in a MarkovDecision Process...
This paper proposes a simple linear Bayesian approachto reinforcement learning. We show thatwith an ...
We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov...
Abstract The problem of reinforcement learning in a non-Markov environment isexplored using a dynami...
This paper proposes a simple linear Bayesian ap-proach to reinforcement learning. We show that with ...
We present a Bayesian reinforcement learning model with a working memory module which can solve some...
The paper deals with the problem of reconstructing a continuous one-dimensional function from discre...
Markov Decision Processes are a mathematical framework widely used for stochastic optimization and c...
We consider an autonomous agent operating in a stochastic, partially-observable, multiagent environm...
Effectively leveraging model structure in reinforcement learning is a difficult task, but failure to...
My research attempts to address on-line action selection in reinforcement learning from a Bayesian p...
Bayesian Reinforcement Learning has generated substantial interest recently, as it provides an elega...
Probabilistic inference is at the core of many recent advances in machine learning. Unfortunately, ...
We propose the use of Model Predictive Control (MPC) for controlling systems described by Markov dec...
This work addresses the problem of estimating the optimal value function in a Markov Decision Proces...
This work addresses the problem of estimating the optimal value function in a MarkovDecision Process...
This paper proposes a simple linear Bayesian approachto reinforcement learning. We show thatwith an ...
We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov...
Abstract The problem of reinforcement learning in a non-Markov environment isexplored using a dynami...
This paper proposes a simple linear Bayesian ap-proach to reinforcement learning. We show that with ...
We present a Bayesian reinforcement learning model with a working memory module which can solve some...
The paper deals with the problem of reconstructing a continuous one-dimensional function from discre...
Markov Decision Processes are a mathematical framework widely used for stochastic optimization and c...
We consider an autonomous agent operating in a stochastic, partially-observable, multiagent environm...
Effectively leveraging model structure in reinforcement learning is a difficult task, but failure to...
My research attempts to address on-line action selection in reinforcement learning from a Bayesian p...
Bayesian Reinforcement Learning has generated substantial interest recently, as it provides an elega...
Probabilistic inference is at the core of many recent advances in machine learning. Unfortunately, ...
We propose the use of Model Predictive Control (MPC) for controlling systems described by Markov dec...