4.3k citations · 6.9k across the 51 of their papers we have counts for
3 papers · 1 filter
Improving Policy Gradient by Exploring Under-appreciated Rewards
Ofir Nachum, Mohammad Norouzi, Dale Schuurmans
This paper presents a novel form of policy gradient for model-free reinforcement learning (RL) with improved exploration properties. Current policy-based methods use entropy regula…
Reward Augmented Maximum Likelihood for Neural Structured Prediction
Mohammad Norouzi, Samy Bengio, Zhifeng Chen +4
A key problem in structured output prediction is direct optimization of the task reward function that matters for test evaluation. This paper presents a simple and computationally…
Stochastic Neural Networks with Monotonic Activation Functions
Siamak Ravanbakhsh, Barnabas Poczos, Jeff Schneider +2
We propose a Laplace approximation that creates a stochastic unit from any smooth monotonic activation function, using only Gaussian noise. This paper investigates the application…