Search Results for author: Tom Blau

Found 4 papers, 2 papers with code

Optimizing Sequential Experimental Design with Deep Reinforcement Learning

no code implementations2 Feb 2022 Tom Blau, Edwin V. Bonilla, Amir Dezfouli, Iadine Chades

Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging.

Experimental Design reinforcement-learning

Learning from Demonstration without Demonstrations

1 code implementation17 Jun 2021 Tom Blau, Gilad Francis, Philippe Morere

To address this shortcoming, we propose Probabilistic Planning for Demonstration Discovery (P2D2), a technique for automatically discovering demonstrations without access to an expert.

Reinforcement Learning with Probabilistically Complete Exploration

no code implementations20 Jan 2020 Philippe Morere, Gilad Francis, Tom Blau, Fabio Ramos

Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL).

reinforcement-learning

Bayesian Curiosity for Efficient Exploration in Reinforcement Learning

1 code implementation20 Nov 2019 Tom Blau, Lionel Ott, Fabio Ramos

Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy.

Efficient Exploration reinforcement-learning

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