Topic

Reinforcement Learning

Latest viewpoints

Human interventions and a value function improve scalable robot learning

Scalable reinforcement learning for robotics can be achieved by using human interventions to avoid dead-end trajectories and by training a general-purpose value function to amortize attempts across tasks, improving reliability significantly.

Chelsea Finn Reinforcement Learning Source at 6:44

Control problems are solved using transition functions and policies.

The speaker defines the core elements of a control problem: a state, an action (control input), a world model (state transition function), and a policy (what action to take given a state).

Francois Chaubard Reinforcement Learning Source at 8:26

Non-differentiable stochastic systems require reinforcement learning methods.

When an environment becomes stochastic and non-differentiable (e.g., due to an unpredictable adversary), direct optimization fails, necessitating reinforcement learning techniques like value iteration or actor-critic.

Francois Chaubard Reinforcement Learning Source at 12:41

World models help estimate value functions and joint state-action distributions.

The speaker clarifies that in standard reinforcement learning, machine learning models are used to estimate value functions, and world models provide a framework for jointly modeling state transitions and policies to create more intelligent behavior.

Ankit Gupta Reinforcement Learning Source at 16:19

Model-free reinforcement learning predicts actions directly from states.

The speaker defines model-free reinforcement learning as a method that learns a policy (action from state) without an explicit model of the environment's dynamics, analogous to behavior cloning or next-token prediction.

Francois Chaubard Reinforcement Learning Source at 41:28

Model-based reinforcement learning uses a world model for planning.

The speaker contrasts model-free methods with model-based RL, where an explicit world model (the transition function) is used to plan actions, enabling stronger policies but requiring more computation for test-time inference.

Francois Chaubard Reinforcement Learning Source at 42:21

Leaders

Jensen Huang

CEO, Nvidia

Last interview Sep 2, 2026

Howard Lutnick

Public business viewpoint profile

Last interview Sep 2, 2026

Sam Altman

CEO, OpenAI

Last interview Sep 2, 2026

Elon Musk

CEO, SpaceX / Tesla

Last interview Sep 1, 2026

Julien Bek

Partner, Sequoia Capital

Last interview Aug 24, 2026

Thibault Sottiaux

Engineer, OpenAI

Last interview Aug 24, 2026

Matthew Berman

Influencer, Forward Future

Last interview Aug 24, 2026

David Senra

Podcaster, Senra Show

Last interview Aug 23, 2026

LeAnn Foster

Founder, EUTHENICS

Last interview Aug 22, 2026

Eric Ho

CEO, Goodfire

Last interview Aug 21, 2026