Skip to content
TLexDR
Episodes / Leslie Kaelbling: Reinforcement Learning, Planning, and Robo...

Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics

05-28-26 ▶ 1h 1m 📖 2 min read
Core Takeaways
Leslie Kaelbling transitioned from philosophy to AI, leveraging symbolic systems to bridge the two fields.
Why it matters Kaelbling's interdisciplinary approach highlights the importance of diverse academic foundations in AI innovation.
Abstraction and Markov Decision Processes (MDPs) are crucial for managing complexity and uncertainty in AI systems. ▶ 6:00
Why it matters MDPs and abstraction are essential for developing AI that can effectively operate in uncertain environments.
Hierarchical planning in AI allows for breaking down long-term goals into manageable tasks, aiding robotic reasoning. ▶ 9:00
Why it matters Hierarchical planning is key to advancing robotic capabilities, enabling more autonomous and efficient operations.
Leslie founded the Journal of Machine Learning Research to address high costs and access issues in academic publishing. ▶ 12:00
Why it matters This shift towards open access publishing democratizes knowledge and encourages deeper, long-term research.
Engineering intelligent robots requires balancing introspection programming with training large neural networks. ▶ 15:00
Why it matters This balance is crucial for creating robots that are both adaptable and efficient, impacting future AI development.

Detailed Insights

Philosophy and AI
+
Leslie Kaelbling's background in philosophy informs her approach to AI.
Symbolic systems serve as a bridge between philosophical concepts and AI.
Philosophical questions about belief and knowledge are relevant to AI research.
Abstraction and Markov Decision Processes
+
Abstraction reduces complexity in AI problem-solving.
MDPs model uncertainty in AI, while POMDPs handle incomplete information.
Optimal planning for POMDPs often requires approximations.
Hierarchical Planning and Robotics
+
Hierarchical planning divides long-term goals into manageable tasks.
Temporal hierarchy helps manage long execution tasks in robotics.
Understanding perception is more complex than planning in AI.
Academic Publishing in AI
+
Leslie founded the Journal of Machine Learning Research to address publishing issues.
The journal operates as an open access platform, challenging traditional models.
Current publishing models discourage long-term, deep research.
Engineering Intelligent Robots
+
Balancing introspection programming with neural networks is key in robotics.
The optimal combination of learning and not learning is crucial for robotics.

How the conversation moved

The episode begins with Leslie Kaelbling reflecting on her academic journey from philosophy to AI, emphasizing how her background in symbolic systems has informed her work in robotics and AI. She outlines the philosophical underpinnings that continue to influence AI research, particularly in areas like belief and knowledge, which are crucial for developing intelligent systems. This sets the stage for a broader discussion on the evolution of AI from its early days focused on cybernetics to its current state, which increasingly mirrors human-like intelligence.

Kaelbling then delves into the technical aspects of AI, particularly the role of abstraction and Markov Decision Processes (MDPs) in managing complexity and uncertainty. She explains how these tools help reduce the state space and horizon in complex problems, making them more tractable for AI systems. The conversation also touches on Partially Observable Markov Decision Processes (POMDPs), which address the challenge of incomplete information, highlighting the need for approximations in optimal planning.

Despite the depth of the discussion, there was a notable lack of pushback from the host, Lex Fridman, on Kaelbling's assertions. This absence of challenge leaves some claims, such as the undecidability of optimal planning for POMDPs, without exploration of potential counterarguments or alternative perspectives. The conversation could have benefited from a deeper examination of these claims, perhaps questioning the feasibility of implementing such complex models in real-world scenarios.

The episode concludes with Kaelbling discussing the founding of the Journal of Machine Learning Research, highlighting issues with the current academic publishing model. She critiques the pressure on students to publish frequently, which she believes undermines long-term, deep research. Kaelbling argues for a future in AI that balances algorithm engineering with the careful design of objective functions, emphasizing the importance of value alignment. This pivot to publishing and research culture underscores her commitment to fostering an environment conducive to meaningful scientific progress.

Surprising moments

Leslie Kaelbling
Leslie Kaelbling noted that less than half of her philosophy classmates pursued computer science, highlighting a common connection between the fields.
Share this quote X Bluesky LinkedIn Email Download card
Leslie Kaelbling
Kaelbling founded the Journal of Machine Learning Research to combat high costs and access issues in academic publishing.

Topics Covered

Philosophy and AI Abstraction and Markov Decision Processes Hierarchical Planning and Robotics Academic Publishing in AI Engineering Intelligent Robots

Memorable Quotes

"I think that there are important questions still about what you can do with a machine and what you can't and so on." — Leslie Kaelbling
"I think you can appreciate much better the good solutions once you've messed around a little bit on your own and found a bad one." — Leslie Kaelbling
"The main roadblock, I think, was that the idea that humans could articulate their knowledge effectively into some kind of logical statements." — Leslie Kaelbling
"I like to say that I'm interested in doing a very bad job of very big problems." — said_on_episode
"I do research because it's fun, not because I care about what we produce." — Leslie

Still open

Unresolved by the end of the conversation

  • Leslie Kaelbling questioned whether robots could be behaviorally indistinguishable from humans, raising philosophical issues about internal distinctions.
  • Kaelbling expressed uncertainty about what structures could be built into AI systems to enhance learning efficiency.

Jargon glossary

Markov Decision Processes (MDPs)
Mathematical frameworks for modeling decision-making in situations where outcomes are partly random.
Partially Observable Markov Decision Processes (POMDPs)
Extensions of MDPs that handle situations with incomplete information.
Hierarchical Planning
A method in AI for breaking down complex tasks into smaller, manageable sub-tasks.

References & Resources

Gödel, Escher, Bach by Douglas Hofstadter book
Journal of Machine Learning Research by Leslie Valiant other

For the specialist

What a senior practitioner would find new

  • Kaelbling's use of symbolic systems from her philosophy background provides a unique approach to AI, bridging abstract concepts with practical applications.
  • The Journal of Machine Learning Research's open access model challenges traditional publishing norms, promoting wider dissemination of knowledge.

Ask this episode Deep

A preview of how Deep chat answers, grounded in this episode with citations and timestamps:

Cite this episode

For papers, blog posts, anywhere.

Copied!

Related episodes

Where to go next from this conversation.

AI-generated summary · last refreshed 2026-06-08 20:28:30 · how we make these

Quotes are matched verbatim against the source transcript; references are checked to resolve to real URLs. Even so, AI can misread structure or attribute claims imperfectly. If you spot an error, please let us know.

Report an inaccuracy →