✳flâneur — a map of the web's best reading
Why do Policy Gradient Methods work so well in Cooperative MARL? Evidence from Policy Representation – The Berkeley Artificial Intelligence Research Blog
bair.berkeley.edu · 1,357 words · saved by 1 readers
The BAIR Blog
In cooperative multi-agent reinforcement learning (MARL), due to its on-policy nature, policy gradient (PG) methods are typically believed to be less sample efficient than value decomposition (VD) methods, which are off-policy . However, some recent empirical studies demonstrate that with proper input representation and hyper-parameter tuning, multi-agent PG can achieve surprisingly strong performance compared to off-policy VD methods. Why could PG methods work so well? In this post, we will present concrete analysis to show that in certain scenarios, e.g., environments with a highly multi-mod
Explore this link on the map →related reading
- The 37 Implementation Details of Proximal Policy Optimization · The ICLR Blog Trackiclr-blog-track.github.io
- Policy Gradient Algorithms | Lil'Loglilianweng.github.io
- A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
- MARLlib: A Multi-agent Reinforcement Learning Library — MARLlib v1.0.0 documentationmarllib.readthedocs.io
- Part 1: Key Concepts in RL - Spinning Up documentationspinningup.openai.com
- A vision researcher’s guide to some RL stuff: PPO & GRPO - Yuge (Jimmy) Shiyugeten.github.io
- State of RL for reasoning LLMs | A. Weersaweers.de
- Reevaluating Policy Gradient Methods for Imperfect-Information Gamesarxiv.org
- JaxMARL: Multi-Agent RL, but 10000x Fasterblog.foersterlab.com
- Learning Beyond Gradientstrinkle23897.github.io
- VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pokémonarxiv.org
- pistar06.pdfpi.website