Reinforcement Learning Pretraining for Reinforcement Learning Finetuning

preview_player
Показать описание
Lecture by Prof. Sergey Levine covering two recent works:
  1. RAIL
Рекомендации по теме
Reinforcement Learning Pretraining 0:51:03

Reinforcement Learning Pretraining for Reinforcement Learning Finetuning

Yuqing Du & 0:52:21

Yuqing Du & Olivia Watkins, Guiding Pretraining in Reinforcement Learning with LLMs, 3.April.202...

Reinforcement Learning from 0:11:29

Reinforcement Learning from Human Feedback (RLHF) Explained

AI Trends 2023: 1:07:12

AI Trends 2023: Reinforcement Learning - RLHF, Robotic Pre-Training & Offline RL with Sergey Lev...

Pre-training for Robots: 0:08:44

Pre-training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials

Deep Reinforcement Learning 0:29:19

Deep Reinforcement Learning with Real-World Data

Reinforcement Learning with 0:22:15

Reinforcement Learning with Augmented Data (Paper Explained)

BERT vs GPT 0:01:00

BERT vs GPT

LLM Post Pretraining 0:28:12

LLM Post Pretraining Pipeline - MUST KNOW for all LLM DEVELOPERS

Supervised Pretraining for 0:12:58

Supervised Pretraining for In-Context Reinforcement Learning with Transformers

FastRLAP: A System 0:04:49

FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing (Summary)

SMART: SELF-SUPERVISED MULTI-TASK 0:08:26

SMART: SELF-SUPERVISED MULTI-TASK PRETRAINING WITH CONTROL TRANSFORMERS (ICLR'23)

Offline Reinforcement Learning 0:51:34

Offline Reinforcement Learning

CVPR 2021 Keynote 0:48:04

CVPR 2021 Keynote -- Pieter Abbeel -- Towards a General Solution for Robotics.

Making Real-World Reinforcement 0:38:23

Making Real-World Reinforcement Learning Practical

The Case for 0:25:17

The Case for Real-World Reinforcement Learning

StriderNET: Graph Reinforcement 0:04:56

StriderNET: Graph Reinforcement Learning to Optimize Atomic Structures | ICML 2023

CS 285: Lecture 0:38:01

CS 285: Lecture 15, Part 1: Offline Reinforcement Learning

Reinforcement Learning from 1:00:38

Reinforcement Learning from Human Feedback: From Zero to chatGPT

Can Wikipedia Help 0:38:35

Can Wikipedia Help Offline Reinforcement Learning? (Paper Explained)

[AUTOML23] A Tutorial 1:33:41

[AUTOML23] A Tutorial on MetaReinforcement Learning

Agent Learns to 0:24:46

Agent Learns to do Reinforcement Learning

Reinforcement Learning: ChatGPT 0:06:31

Reinforcement Learning: ChatGPT and RLHF

Deep Reinforcement Learning 0:25:40

Deep Reinforcement Learning in Production at Zynga | Patrick Halina & Mehdi Ben Ayed

Комментарии
Автор

Why does the absolute Q value matter? I only need to know the relative Q-value.

ZhenghaoChi
Автор

Thank you for another awesome talk, I love your material and for me you have the best DL and RL courses, thanks for sharing them and contributing to the democratization of knowledge

AnasBELFADIL
Автор

Is the equation for CAL-QL the same for the paper and this video or did it change

nileshramgolam