Exploring Restart Distributions

no code implementations • 27 Nov 2018 • Arash Tavakoli, Vitaly Levdik, Riashat Islam, Christopher M. Smith, Petar Kormushev

We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution.

Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks

2 code implementations • ICLR 2019 • Fabio Pardo, Vitaly Levdik, Petar Kormushev

Being able to reach any desired location in the environment can be a valuable asset for an agent.

Montezuma's Revenge Navigate +4

Goal-oriented Trajectories for Efficient Exploration

no code implementations • 5 Jul 2018 • 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 novelty.

Efficient Exploration reinforcement-learning +1

Time Limits in Reinforcement Learning

1 code implementation • ICML 2018 • Fabio Pardo, Arash Tavakoli, Vitaly Levdik, Petar Kormushev

In case (ii), the time limits are not part of the environment and are only used to facilitate learning.

General Reinforcement Learning reinforcement-learning +1