Search Results for author: Ehsan Imani

Found 4 papers, 0 papers with code

Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models

no code implementations8 Jun 2020 Taher Jafferjee, Ehsan Imani, Erin Talvitie, Martha White, Micheal Bowling

Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environment model.

An implicit function learning approach for parametric modal regression

no code implementations NeurIPS 2020 Yangchen Pan, Ehsan Imani, Martha White, Amir-Massoud Farahmand

We empirically demonstrate on several synthetic problems that our method (i) can learn multi-valued functions and produce the conditional modes, (ii) scales well to high-dimensional inputs, and (iii) can even be more effective for certain uni-modal problems, particularly for high-frequency functions.

An Off-policy Policy Gradient Theorem Using Emphatic Weightings

no code implementations NeurIPS 2018 Ehsan Imani, Eric Graves, Martha White

There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence of the policy gradient theorem which provides a simplified form for the gradient.

Policy Gradient Methods

Improving Regression Performance with Distributional Losses

no code implementations ICML 2018 Ehsan Imani, Martha White

We provide theoretical support for this alternative hypothesis, by characterizing the norm of the gradients of this loss.

Cannot find the paper you are looking for? You can Submit a new open access paper.