Multi-agent reinforcement learning: A selective overview of theories and algorithms
Recent years have witnessed significant advances in reinforcement learning (RL), which
has registered tremendous success in solving various sequential decision-making problems …
has registered tremendous success in solving various sequential decision-making problems …
An overview of multi-agent reinforcement learning from game theoretical perspective
Y Yang, J Wang - arXiv preprint arXiv:2011.00583, 2020 - arxiv.org
Following the remarkable success of the AlphaGO series, 2019 was a booming year that
witnessed significant advances in multi-agent reinforcement learning (MARL) techniques …
witnessed significant advances in multi-agent reinforcement learning (MARL) techniques …
Mastering the game of Stratego with model-free multiagent reinforcement learning
We introduce DeepNash, an autonomous agent that plays the imperfect information game
Stratego at a human expert level. Stratego is one of the few iconic board games that artificial …
Stratego at a human expert level. Stratego is one of the few iconic board games that artificial …
[PDF][PDF] Nash learning from human feedback
Large language models (LLMs)(Anil et al., 2023; Glaese et al., 2022; OpenAI, 2023; Ouyang
et al., 2022) have made remarkable strides in enhancing natural language understanding …
et al., 2022) have made remarkable strides in enhancing natural language understanding …
Independent policy gradient methods for competitive reinforcement learning
C Daskalakis, DJ Foster… - Advances in neural …, 2020 - proceedings.neurips.cc
We obtain global, non-asymptotic convergence guarantees for independent learning
algorithms in competitive reinforcement learning settings with two agents (ie, zero-sum …
algorithms in competitive reinforcement learning settings with two agents (ie, zero-sum …
Language agents with reinforcement learning for strategic play in the werewolf game
Agents built with large language models (LLMs) have recently achieved great
advancements. However, most of the efforts focus on single-agent or cooperative settings …
advancements. However, most of the efforts focus on single-agent or cooperative settings …
Fictitious play for mean field games: Continuous time analysis and applications
S Perrin, J Pérolat, M Laurière… - Advances in neural …, 2020 - proceedings.neurips.cc
In this paper, we deepen the analysis of continuous time Fictitious Play learning algorithm to
the consideration of various finite state Mean Field Game settings (finite horizon, $\gamma …
the consideration of various finite state Mean Field Game settings (finite horizon, $\gamma …
Student of Games: A unified learning algorithm for both perfect and imperfect information games
Games have a long history as benchmarks for progress in artificial intelligence. Approaches
using search and learning produced strong performance across many perfect information …
using search and learning produced strong performance across many perfect information …
Independent natural policy gradient always converges in markov potential games
Natural policy gradient has emerged as one of the most successful algorithms for computing
optimal policies in challenging Reinforcement Learning (RL) tasks, yet, very little was known …
optimal policies in challenging Reinforcement Learning (RL) tasks, yet, very little was known …
Escaping the gravitational pull of softmax
The softmax is the standard transformation used in machine learning to map real-valued
vectors to categorical distributions. Unfortunately, this transform poses serious drawbacks for …
vectors to categorical distributions. Unfortunately, this transform poses serious drawbacks for …