🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

1/ 🚀 Presenting AGI - Artificial Generational Intelligence 🚀 We apply the concept of cultural accumulation to RL and find that agents can improve across generations, outperforming those trained for a single lifetime of the same experience budget! Co-led w/ Chris Lu. 🧵

Excited to share my first work from my internship Sakana AI! We used LLMs to design and implement new preference optimization algorithms for training LLMs, discovering cutting-edge methods! Co-led with Sam Holt and Claudio Fanconi. Details in thread 🧵 (1/N)

1 / 🧵 Excited to introduce our #ICML2024 paper: 😈 EvIL (Evolution Strategies for Generalisable Imitation Learning) a new inverse RL (IRL) method for sample efficient transfer of expert behaviour across environments – it's so good, it's downright EvIL!

DQN kick-started the field of deep RL 12 years ago, but Q-learning has recently taken a backseat compared to PPO and other on-policy method. We introduce PQN, a greatly simplified version of DQN which is highly GPU compatible and theoretically supported by convergence proofs.

Matteo Gallici Very interesting work! It sounds very similar to our CrossQ paper x.com/aditya_bhatt/s…

Really impactful work, most prominently in finally figuring out how to bring the speed increases of Jax to off-policy value-based algorithms! Another building block falls into place in the Jax RL ecosystem..

This paper looks super cool. I've started reading it and am really enjoying the clarity of exposition, theoretical investigation, and simplicity of resulting algorithm.

1/ 🤖 Learned optimization offers huge potential to automate machine learning! So why doesn't it work well in RL (and how did we fix it)?! I'm excited to share OPEN, our AutoRL Workshop spotlight paper exploring this question! 🧵

1/🚀 Foerster Lab for AI Research is coming to #icml2024 in Vienna 🎉 (I am literally posting from the train) and we are very excited to share our work with you! You can find us here ⬇️✨ see below 🔗 for clickable links

We are very excited to announce Kinetix: an open-ended universe of physics-based tasks for RL! We use Kinetix to train a general agent on millions of randomly generated physics problems and show that this agent generalises to unseen handmade environments. 1/🧵

🏋️‍♂️Go from creating an environment to having a trained expert agent within minutes! As part of Kinetix, we are releasing an editor that can create custom physics-based RL environments, and import them seamlessly into an RL training loop. 1/

Roger Creus Castanyer just implemented a CleanRL Parallel Q-Networks algorithm (PQN) implementation! 🚀PQN is DQN without a replay buffer and target network. You can run PQN on GPU environments or vectorized environments. E.g., in envpool, PQN gets DQN's score in 1/10th the time

📢New paper on arXiv: Hadamax Encoding: Elevating Performance in Model-Free Atari. (arxiv.org/abs/2505.15345) Our Hadamax (Hadamard max-pooling) encoder architecture improves the recent PQN algorithm’s Atari performance by 80%, allowing it to significantly surpass Rainbow-DQN!

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks thrilled to share our #ICML2025 paper led by Walter Mayor-Toro & Johan S. Obando 👍🏽 , with Aaron Courville , where we explore how data collection affects agents in parallelized setups. 1/