Nir Baram

3 accepted papers

2021

Action redundancy in reinforcement learning

UAI 2021poster

Maximum Entropy (MaxEnt) reinforcement learning is a powerful learning paradigm which seeks to maximize return under entropy regularization. However, action entropy does not necessarily coincide with state entropy, e.g., when multiple actions produce the same transition. Instead, we propose to maxim…

Cited by 8 Source ↗PDF ↗Scholar ↗

2017

Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning

Oron Anschel, Nir Baram, Nahum Shimkin

ICML 2017poster

Instability and variability of Deep Reinforcement Learning (DRL) algorithms tend to adversely affect their performance. Averaged-DQN is a simple extension to the DQN algorithm, based on averaging previously learned Q-values estimates, which leads to a more stable training procedure and improved perf…

Cited by 432 Source ↗PDF ↗Scholar ↗

2017

End-to-End Differentiable Adversarial Imitation Learning

Nir Baram, Oron Anschel, Itai Caspi, Shie Mannor

ICML 2017poster

Generative Adversarial Networks (GANs) have been successfully applied to the problem of

Cited by 125 Source ↗PDF ↗Scholar ↗