360 citations · 2.7k across the 150 of their papers we have counts for
8 papers · 2 filters
Learnings Options End-to-End for Continuous Action Tasks
Martin Klissarov, Pierre-Luc Bacon, Jean Harb +1
We present new results on learning temporally extended actions for continuoustasks, using the options framework (Suttonet al.[1999b], Precup [2000]). In orderto achieve this goal w…
OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
Peter Henderson, Wei-Di Chang, Pierre-Luc Bacon +3
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for…
Deep Reinforcement Learning that Matters
Peter Henderson, Riashat Islam, Philip Bachman +3
In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning (RL). Reproducing existing work and acc…
Independently Controllable Factors
Valentin Thomas, Jules Pondard, Emmanuel Bengio +6
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of traini…
Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
Riashat Islam, Peter Henderson, Maziar Gomrokchi +1
Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark…
Variational Generative Stochastic Networks with Collaborative Shaping
Philip Bachman, Doina Precup
We develop an approach to training generative models based on unrolling a variational auto-encoder into a Markov chain, and shaping the chain's trajectories using a technique inspi…