Agents
Online Reinforcement Learning in Stochastic Games
Chen-Yu Wei, Yi-Te Hong, Chi-Jen Lu
We study online reinforcement learning in average-reward stochastic games (SGs).
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
In this paper, we first observe that policies learned using InRL can overfit to the other agents' policies during training, failing to sufficiently generalize during execution. We introduce a new metric, joint-policy correlation, to quantify this effect.
Inverse Reward Design
Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart J. Russell, Anca Dragan
Autonomous agents optimize the reward function we give them.
Statistical Cost Sharing
Eric Balkanski, Umar Syed, Sergei Vassilvitskii
Neural Information Processing Systems http://nips.cc/
Countering Feedback Delays in Multi-Agent Learning
Zhengyuan Zhou, Panayotis Mertikopoulos, Nicholas Bambos, Peter W. Glynn, Claire Tomlin
Neural Information Processing Systems http://nips.cc/
A multi-agent reinforcement learning model of common-pool resource appropriation
Humanity faces numerous problems of common-pool resource appropriation.
Multi-View Decision Processes: The Helper-AI Problem
Christos Dimitrakakis, David C. Parkes, Goran Radanovic, Paul Tylkin
We model this setting as a multi-view decision process, which we use to formally analyze the positive effect of steering policies.
Hybrid Reward Architecture for Reinforcement Learning Harm van Seijen
One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network.
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments
Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence.
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
Cao, Shiyi, Li, Dacheng, Zhao, Fangzhou, Yuan, Shuo, Hegde, Sumanth R., Chen, Connor, Ruan, Charlie, Griggs, Tyler, Liu, Shu, Tang, Eric, Liaw, Richard, Moritz, Philipp, Zaharia, Matei, Gonzalez, Joseph E., Stoica, Ion
We introduce SkyRL-Agent, a framework for efficient, multi-turn, long-horizon agent training and evaluation. It provides efficient asynchronous dispatching, lightweight tool integration, and flexible backend interoperability, enabling seamless use with existing RL frameworks such as SkyRL-train, VeRL, and Tinker. Using SkyRL-Agent, we train SA-SWE-32B, a software engineering agent trained from Qwen3-32B (24.4% Pass@1) purely with reinforcement learning. We introduce two key components: an optimized asynchronous pipeline dispatcher that achieves a 1.55x speedup over naive asynchronous batching, and a tool-enhanced training recipe leveraging an AST-based search tool to facilitate code navigation, boost rollout Pass@K, and improve training efficiency. Together, these optimizations enable SA-SWE-32B to reach 39.4% Pass@1 on SWE-Bench Verified with more than 2x cost reduction compared to prior models reaching similar performance. Despite being trained solely on SWE tasks, SA-SWE-32B generalizes effectively to other agentic tasks, including Terminal-Bench, BrowseComp-Plus, and WebArena. We further demonstrate SkyRL-Agent's extensibility through case studies on deep research, computer use, and memory agents, each trained using a different training backend.