A common setting in multitask reinforcement learning (RL) demands that a...
We study the problem of representation learning in stochastic contextual...
A zero-shot RL agent is an agent that can solve any RL task in a given
e...
We introduce the forward-backward (FB) representation of the dynamics of...
We study episodic reinforcement learning in non-stationary linear (a.k.a...
Reinforcement learning (RL) algorithms typically deal with maximizing th...
The Smoothed Bellman Error Embedding algorithm <cit.>,
known as SBEED, w...
We investigate whether Jacobi preconditioning, accounting for the bootst...
Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization...
Despite the wealth of research into provably efficient reinforcement lea...
Recent advances in variational inference enable the modelling of highly
...
Stochastic variance-reduced gradient (SVRG) is an optimization method
or...
In model-based reinforcement learning, the agent interleaves between mod...
In many finite horizon episodic reinforcement learning (RL) settings, it...
Randomized value functions offer a promising approach towards the challe...
This work investigates training Conditional Random Fields (CRF) by Stoch...
In this paper, we study two aspects of the variational autoencoder (VAE)...
Generative modeling of high dimensional data like images is a notoriousl...
Off-policy learning is key to scaling up reinforcement learning as it al...