65 citations · 364 across the 38 of their papers we have counts for
7 papers · 1 filter
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Maximilian Igl, Kamil Ciosek, Yingzhen Li +4
The ability for policies to generalize to new environments is key to the broad application of RL agents. A promising approach to prevent an agent's policy from overfitting to a lim…
Better Exploration with Optimistic Actor-Critic
Kamil Ciosek, Quan Vuong, Robert Loftin +1
Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art perfo…
Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
Rémy Portelas, Cédric Colas, Katja Hofmann +1
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environmen…
Variational Integrator Networks for Physically Structured Embeddings
Steindor Saemundsson, Alexander Terenin, Katja Hofmann +1
Learning workable representations of dynamical systems is becoming an increasingly important problem in a number of application areas. By leveraging recent work connecting deep neu…
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
Luisa Zintgraf, Kyriacos Shiarlis, Maximilian Igl +4
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions…
Combining No-regret and Q-learning
Ian A. Kash, Michael Sullins, Katja Hofmann
Counterfactual Regret Minimization (CFR) has found success in settings like poker which have both terminal states and perfect recall. We seek to understand how to relax these requi…
The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition
Diego Perez-Liebana, Katja Hofmann, Sharada Prasanna Mohanty +5
Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and differ…