Prof Natasha Jaques Multi Agent

Media Summary: Fifth lecture for CSE 599J on Social Reinforcement Learning: In the inaugural episode of the Allen School's “Faculty in Focus” series, Assistant A talk I gave on May 9th about our recent paper, Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer ...

Prof Natasha Jaques Multi Agent - Detailed Analysis & Overview

Fifth lecture for CSE 599J on Social Reinforcement Learning: In the inaugural episode of the Allen School's “Faculty in Focus” series, Assistant A talk I gave on May 9th about our recent paper, Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer ... Fourth lecture for CSE 599J on Social Reinforcement Learning: Multi-agent DQN training step 0 trajectory video Multi-agent DQN training step 90000 trajectory video

Presentation of my thesis "Towards Social and Affective Machine Learning" ... Social learning helps humans and animals rapidly adapt to new circumstances, coordinate with others, and drives the emergence ... We hosted the AI Safety Barcelona inaugural event last Wednesday evening at Universitat de Barcelona and it was a great ... Lecture on reinforcement learning (RL) fine-tuning of large language models (LLMs). Even though we are in the RL era for ...

Photo Gallery

Prof. Natasha Jaques: Multi-agent Reinforcement Learning (MARL) for LLMs

Natasha Jaques - Social Reinforcement Learning - IPAM at UCLA

5 - Deep Multi agent RL

[Audio Descriptions] Faculty In Focus: Natasha Jaques

Self Play for Safety - Online Multi-Agent Adversarial Training for Provably Robust LLMs

4 - Learning from humans beyond LLMs

Multi-agent DQN training step 0 trajectory video

Natasha Jaques - Multi-agent RL for Provably Robust LLM Safety [Alignment Workshop]

Multi-agent DQN training step 90000 trajectory video

Natasha Jaques PhD Thesis Defense

Social Reinforcement Learning talk at RLDM

Lewis Hammond and Natasha Jaques talk AI Safety - AI Safety Barcelona Inaugural event (29/05/24)

View Detailed Profile

Prof. Natasha Jaques: Multi-agent Reinforcement Learning (MARL) for LLMs

Prof. Natasha Jaques: Multi-agent Reinforcement Learning (MARL) for LLMs

Talk Title:

Natasha Jaques - Social Reinforcement Learning - IPAM at UCLA

Natasha Jaques - Social Reinforcement Learning - IPAM at UCLA

Recorded 19 February 2022.

5 - Deep Multi agent RL

5 - Deep Multi agent RL

Fifth lecture for CSE 599J on Social Reinforcement Learning: https://courses.cs.washington.edu/courses/cse599j1/25au/.

[Audio Descriptions] Faculty In Focus: Natasha Jaques

[Audio Descriptions] Faculty In Focus: Natasha Jaques

In the inaugural episode of the Allen School's “Faculty in Focus” series, Assistant

Self Play for Safety - Online Multi-Agent Adversarial Training for Provably Robust LLMs

Self Play for Safety - Online Multi-Agent Adversarial Training for Provably Robust LLMs

A talk I gave on May 9th about our recent paper, Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer ...

4 - Learning from humans beyond LLMs

4 - Learning from humans beyond LLMs

Fourth lecture for CSE 599J on Social Reinforcement Learning: https://courses.cs.washington.edu/courses/cse599j1/25au/.

Multi-agent DQN training step 0 trajectory video

Multi-agent DQN training step 0 trajectory video

Multi-agent DQN training step 0 trajectory video

Natasha Jaques - Multi-agent RL for Provably Robust LLM Safety [Alignment Workshop]

Natasha Jaques - Multi-agent RL for Provably Robust LLM Safety [Alignment Workshop]

Natasha Jaques

Multi-agent DQN training step 90000 trajectory video

Multi-agent DQN training step 90000 trajectory video

Multi-agent DQN training step 90000 trajectory video

Natasha Jaques PhD Thesis Defense

Natasha Jaques PhD Thesis Defense

Presentation of my thesis "Towards Social and Affective Machine Learning" ...

Social Reinforcement Learning talk at RLDM

Social Reinforcement Learning talk at RLDM

Social learning helps humans and animals rapidly adapt to new circumstances, coordinate with others, and drives the emergence ...

Lewis Hammond and Natasha Jaques talk AI Safety - AI Safety Barcelona Inaugural event (29/05/24)

Lewis Hammond and Natasha Jaques talk AI Safety - AI Safety Barcelona Inaugural event (29/05/24)

We hosted the AI Safety Barcelona inaugural event last Wednesday evening at Universitat de Barcelona and it was a great ...

Reinforcement Learning (RL) for LLMs

Reinforcement Learning (RL) for LLMs

Lecture on reinforcement learning (RL) fine-tuning of large language models (LLMs). Even though we are in the RL era for ...