Rishabh Agarwal - Deep reinforcement learning at the edge of the statistical precipice

preview_player
Показать описание
UoE RL Reading Group | 13 January 2022

Speaker: Rishabh Agarwal (Google DeepMind)

Title: Deep reinforcement learning at the edge of the statistical precipice

Authors: Agarwal, Rishabh, Max Schwarzer, Pablo Samuel Castro, Aaron Courville, and Marc G. Bellemare

In: International Conference on Machine Learning, pp. 2388-2397. PMLR, 2021.

  1. UoE Agents Group
  2. rl
  3. reinforcement learning
Рекомендации по теме
Rishabh Agarwal - 0:37:20

Rishabh Agarwal - Deep reinforcement learning at the edge of the statistical precipice

Deep Reinforcement Learning 0:50:23

Deep Reinforcement Learning at the Edge of the Statistical Precipice with Rishabh Agarwal - #559

Deep RL at 0:14:12

Deep RL at the Edge of the Statistical Precipice (NeurIPS Best Paper)

2022 AI Seminar 0:50:48

2022 AI Seminar Series: Rishabh Agarwal - How to Avoid Fooling Ourselves in Deep RL research

Neural Additive Models: 0:02:55

Neural Additive Models: Interpretable Machine Learning with Neural Nets

Self-generated data @ 0:56:41

Self-generated data @ DLCT

Séminaire DIC-ISC-CRIA - 1:08:50

Séminaire DIC-ISC-CRIA - 3 octobre 2024 par Rishabh AGARWAL

Reincarnating RL @ 0:50:17

Reincarnating RL @ DLCT

Deep Reinforcement Learning 0:14:05

Deep Reinforcement Learning at the Edge of Statistical Precipice | Outstanding Paper | NeurIPS'...

Implicit Under-Parameterization Inhibits 0:12:25

Implicit Under-Parameterization Inhibits Data-Efficient Deep RL

DR3: Value-Based Deep 0:15:53

DR3: Value-Based Deep RL Requires Explicit Regularization

Most Embarrassing Intro?! 0:00:28

Most Embarrassing Intro?! ft. Nikita Pawar | Ranveer Allahbadia Shorts

Learning to Generalize 0:04:17

Learning to Generalize from Sparse and Underspecified Rewards (ICML'19)

Tea Time Talks 0:37:40

Tea Time Talks 2024: Parham Panahi, Experience Selection in Deep RL

Googles answer to 0:09:33

Googles answer to OpenAI's o1 'Training Language Models to Self-Correct via Reinforcement...

What is the 1:10:17

What is the Statistical Complexity of Reinforcement Learning?

KDD 2020: Lecture 3:29:02

KDD 2020: Lecture Style Tutorials: Advances in Recommender Systems

Charline Le Lan 0:42:50

Charline Le Lan - On the Generalization of Representations in Reinforcement Learning

Online Reinforcement Learning 0:30:51

Online Reinforcement Learning With The Help Of Confounded Offline Data

Harvard Medical AI: 0:20:29

Harvard Medical AI: Sina Hartung on 'Reinforce. Learning at the Edge of the Statistical Precipi...

One Thing You 0:08:26

One Thing You Must Do To Stay Relevant In The AI Era

Training LLM to 0:06:29

Training LLM to Self-Correct via Reinforcement Learning - Audio Podcast with Google NotebookLM

This DeepMind New 1:31:32

This DeepMind New RL Method is INSANELY GOOD

On the Expressivity 0:47:40

On the Expressivity of Markov Reward [NeurIPS 2021 Outstanding Paper] - Research Paper Explained!