Vivek Myers
@vivek_myers
Followers
1K
Following
3K
Media
32
Statuses
147
PhD student @Berkeley_AI | reinforcement learning | 🦋 @ https://t.co/KcNnhdfr5m
Joined December 2019
RT @esfrankel: Tomorrow, I'm excited to present "Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agen….
0
2
0
RT @ajwagenmaker: How can we train a foundation model to internalize what it means to “explore”?. Come check out our work on “behavioral ex….
0
50
0
RT @qiyang_li: Everyone knows action chunking is great for imitation learning. It turns out that we can extend its success to RL to better….
0
65
0
RT @ajwagenmaker: Diffusion policies have demonstrated impressive performance in robot control, yet are difficult to improve online when 0-….
0
59
0
RT @siddkaramcheti: Thrilled to share that I'll be starting as an Assistant Professor at Georgia Tech (@ICatGT / @GTrobotics / @mlatgt) in….
0
27
0
RT @seohong_park: Q-learning is not yet scalable. I wrote a blog post about my thoughts on scalable RL algorithms.….
0
188
0
RT @chongyiz1: 1/ How should RL agents prepare to solve new tasks? While prior methods often learn a model that predicts the immediate next….
0
33
0
RT @seohong_park: New paper on unsupervised pre-training for RL!. The idea is to learn a flow-based future prediction model for each "inten….
0
20
0
RT @YifeiZhou02: 📢 New Preprint: Self-Challenging Agent (SCA) 📢. It’s costly to scale agent tasks with reliable verifiers. In SCA, the key….
0
37
0
RT @verityw_: Embodied chain-of-thought reasoning (ECoT) is a powerful way to improve robot generalization & performance. But why is this t….
0
11
0
How can we learn the reward functions of multiple agents from unlabeled data? We model interactions between learned models of the agent objectives (marginalized 𝑄 functions) when performing inverse RL to learn mixed cooperative/competitive environments. See @ebiyik_'s thread ↓.
In another ICRA 2025 paper, we developed a multi-agent inverse reinforcement learning method. As opposed to existing solutions, our method does not make assumptions about the reward structure -- it can be an environment that is neither fully cooperative nor fully competitive.
0
0
11
RT @amyxlu: Gave my PhD dissertation talk! 🧬 Tried my best to make AI for drug discovery & protein design accessible for ML folks:. Beyond….
0
72
0
RT @ebiyik_: In another ICRA 2025 paper, we developed a multi-agent inverse reinforcement learning method. As opposed to existing solutions….
0
2
0
Presenting w/ Cathy Ji and @ben_eysenbach . Thread:
Reinforcement learning should be able to improve upon behaviors seen when training. In practice, RL agents often struggle to generalize to new long-horizon behaviors. Our new paper studies *horizon generalization*, the degree RL algorithms generalize to reaching distant goals. 1/
0
0
0
RT @m_bortkiewicz: Excited to present JaxGCRL at ICLR 2025 (spotlight):. 📍Hall 3 + Hall 2B, Poster #422.🗓️Friday, April 25.🕒3:00 PM – 5:00….
0
3
0
GitHub: See @m_bortkiewicz's thread for details:.
github.com
Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight. - MichalBortkiewicz/JaxGCRL
I am excited to share our recent work with @WladekPalucki , @vivek_myers, @Taddziarm , @tomArczewski, @LukeKucinski, and @ben_eysenbach!. Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research . Webpage:
0
0
2
Working on goal-conditioned RL? 𝙹𝚊𝚡𝙶𝙲𝚁𝙻 offers 10+ GPU-accelerated environments (up to 22× faster) with strong GCRL baselines—ideal for rapid iteration and benchmarking. Now on PyPI!.𝚙𝚒𝚙 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚓𝚊𝚡𝚐𝚌𝚛𝚕
1
0
17
RT @cassidy_laidlaw: We built an AI assistant that plays Minecraft with you. Start building a house—it figures out what you’re doing and ju….
0
217
0
RT @a_lidayan: 🚨Our new #ICLR2025 paper presents a unified framework for intrinsic motivation and reward shaping: they signal the value of….
0
31
0