3 papers
cs.LG2018
Exploring Restart Distributions
Arash Tavakoli, Vitaly Levdik, Riashat Islam +2
We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those cor…
cs.LG2018
Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
Fabio Pardo, Vitaly Levdik, Petar Kormushev
Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often no…
cs.LG2018
Goal-oriented Trajectories for Efficient Exploration
Fabio Pardo, Vitaly Levdik, Petar Kormushev
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novel…