Tim Rocktäschel's guest appearances

Tim Rocktäschel

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

NLP Highlights

MIXEDCAST: Podcast über VR, AR, KI

Towards Data Science

DEEP MINDS - KI-Podcast

Emily Bender

Emmanuel Ameisen

Alona Fyshe

Sameer Singh

Max Welling

Roland Memisevic

Solmaz Shahalizadeh

Sebastian Ruder

Mike Tung

David Duvenaud

Jeremy Howard

Margaret Mitchell

Thomas Wolf

Burr Settles

Sam Bowman

OwlTail

Take our survey at twimlai.com/survey21!Today we’re joined by Tim Rocktäschel, a research scientist at Facebook AI Research and an associate professor at University College London (UCL). Tim’s work focuses on training RL agents in simulated environments, with the goal of these agents being able to generalize to novel situations. Typically, this is done in environments like OpenAI Gym, MuJuCo, or even using Atari games, but these all come with constraints. In Tim’s approach, he utilizes a game called NetHack, which is much more rich and complex than the aforementioned environments.  In our conversation with Tim, we explore the ins and outs of using NetHack as a training environment, including how much control a user has when generating each individual game and the challenges he's faced when deploying the agents. We also discuss his work on MiniHack, an environment creation framework and suite of tasks that are based on NetHack, and future directions for this research.The complete show notes for this episode can be found at twimlai.com/go/527.

Take our survey at <a href="https://twimlai.com/survey21" rel="nofollow" target="_blank">twimlai.com/survey21</a>! Today we’re joined by Tim Rocktäschel, a research scientist at Facebook AI Research and an associate professor at University College London (UCL).  Tim’s work focuses on training RL agents in simulated environments, with the goal of these agents being able to generalize to novel situations. Typically, this is done in environments like OpenAI Gym, MuJuCo, or even using Atari games, but these all come with constraints. In Tim’s approach, he utilizes a game called NetHack, which is much more rich and complex than the aforementioned environments.   In our conversation with Tim, we explore the ins and outs of using NetHack as a training environment, including how much control a user has when generating each individual game and the challenges he's faced when deploying the agents. We also discuss his work on MiniHack, an environment creation framework and suite of tasks that are based on NetHack, and future directions for this research. The complete show notes for this episode can be found at <a href="twimlai.com/go/527" rel="nofollow" target="_blank">twimlai.com/go/527</a>.

Advancing Deep Reinforcement Learning with NetHack, w/ Tim Rocktäschel - #527

Reinforcement learning can do some pretty impressive things. It can optimize ad targeting, help run self-driving cars, and even win StarCraft games. But current RL systems are still highly task-specific. Tesla’s self-driving car algorithm can’t win at StarCraft, and DeepMind’s AlphaZero algorithm can with Go matches against grandmasters, but can’t optimize your company’s ad spend. So how do we make the leap from narrow AI systems that leverage reinforcement learning to solve specific problems, to more general systems that can orient themselves in the world? Enter Tim Rocktäschel, a Research Scientist at Facebook AI Research London and a Lecturer in the Department of Computer Science at University College London. Much of Tim’s work has been focused on ways to make RL agents learn with relatively little data, using strategies known as sample efficient learning, in the hopes of improving their ability to solve more general problems. Tim joined me for this episode of the podcast.

Reinforcement learning can do some pretty impressive things. It can optimize ad targeting, help run self-driving cars, and even win StarCraft games. But current RL systems are still highly task-specific. Tesla’s self-driving car algorithm can’t win at StarCraft, and DeepMind’s AlphaZero algorithm can with Go matches against grandmasters, but can’t optimize your company’s ad spend. So how do we make the leap from narrow AI systems that leverage reinforcement learning to solve specific problems, to more general systems that can orient themselves in the world? Enter Tim Rocktäschel, a Research Scientist at <a href="https://research.fb.com/category/facebook-ai-research/" rel="noopener nofollow" target="_blank">Facebook AI Research</a> London and a Lecturer in the <a href="http://www.cs.ucl.ac.uk/home" rel="noopener nofollow" target="_blank">Department of Computer Science</a> at <a href="https://www.ucl.ac.uk/" rel="noopener nofollow" target="_blank">University College London</a>. Much of Tim’s work has been focused on ways to make RL agents learn with relatively little data, using strategies known as sample efficient learning, in the hopes of improving their ability to solve more general problems. Tim joined me for this episode of the podcast.

54. Tim Rocktäschel - Deep reinforcement learning, symbolic learning and the road to AGI

An interview with Tim Rocktäschel.https://arxiv.org/abs/1705.11040

An interview with Tim Rocktäschel. <a href="https://arxiv.org/abs/1705.11040" rel="nofollow" target="_blank">https://arxiv.org/abs/1705.11040</a>

19 - End-to-end Differentiable Proving, with Tim Rocktäschel