You Only Live Once: Single-Life Reinforcement Learning
— AK (@_akhaliq) October 18, 2022
abs: https://t.co/PG3tqv89DA pic.twitter.com/WrwzfA2Bg8
You Only Live Once: Single-Life Reinforcement Learning
— AK (@_akhaliq) October 18, 2022
abs: https://t.co/PG3tqv89DA pic.twitter.com/WrwzfA2Bg8
The (Un)Surprising Effectiveness of Pre-Trained Vision Models for Control
— AK (@ak92501) March 8, 2022
abs: https://t.co/kFVZx80f2u pic.twitter.com/Tm723A7aqC
WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU
— AK (@ak92501) September 1, 2021
pdf: https://t.co/6z9WZacJyk
abs: https://t.co/wUX0MThFGc pic.twitter.com/vR6V68Zdgv
A nice multi-agent reinforcement learning library by @instadeepai including our old DIAL method @iassael @j_foerst @shimon8282 - built using Acme https://t.co/F2XmdcA7WM
— Nando de Freitas (@NandoDF) July 27, 2021
RLCard - A Toolkit for Reinforcement Learning in Card Games. https://t.co/UB6RGcCVdS #Python #CardGames pic.twitter.com/SHj50MJWob
— Python Weekly (@PythonWeekly) July 1, 2021
MuZero removed simulators in MBRL vs AlphaGo. VQ Models for Planning generalize to partial observable & stochastic environments. How?
— Oriol Vinyals (@OriolVinyalsML) June 11, 2021
1. Discretize states w/ VQVAE
2. Train a LM over states
3. Plan w/ MCTS using the LM
Led by @yazhe_li & @sherjilozair https://t.co/thvB6Ke1EA pic.twitter.com/tsXGcrweTZ
New work on Efficient Transformers in RL using Actor-Learner Distillation:
— Russ Salakhutdinov (@rsalakhu) April 10, 2021
Compressing online larger “Learner model” towards a tractable “Actor model” in distributed RL setting with partially-observable environments.https://t.co/jnExWiPabS
with E. Parisotto #ICLR2021 pic.twitter.com/kC5SSRsWrn
Excellent example of low-resource ML research showing AlphaZero scaling laws on a single RTX 2080. https://t.co/MGgwzKJPJq
— Eric Jang 🇺🇸🇹🇼 (@ericjang11) April 8, 2021
Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation
— AK (@ak92501) April 6, 2021
pdf: https://t.co/ncLWJgbf6d
abs: https://t.co/ozkZ6WgNRl pic.twitter.com/N2bJv4kd6j
Today we present an approach for iterative digital game design that leverages #MachineLearning to train agents as play-testers, allowing designers to efficiently balance a game and align it with their original vision. Learn more at https://t.co/eAC9UoPBN5 pic.twitter.com/HjqRMcnnez
— Google AI (@GoogleAI) March 19, 2021
20 hours of new lectures on Deep Learning and Reinforcement Learning with lots of examples https://t.co/3cXv2E0rcd
— /MachineLearning (@slashML) February 23, 2021
DreamerV2, a collaboration between DeepMind, @GoogleAI and the @UofT, is the first RL agent based on a world model to achieve human-level performance on the Atari benchmark. Read more ⬇️ https://t.co/lFFuHH2Uk9
— DeepMind (@DeepMind) February 19, 2021