Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Momentum

144 papers in the last four weeks, up 243% on the four weeks before. 1.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,147

All topics

Safe Learning Under Irreversible Dynamics via Asking for Help
Date pendingBenjamin Plaut, Juan Liévano-Karim, Hanlin Zhu +1Regret Minimization in RL Reinforcement Learning
Division of Computer Science University of California Berkeley, CA 94720-1776, USA
AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training
Date pendingZhenyu Han, Ansheng You, Haibo Wang +16RL for Language Models Asynchronous RL
Huawei · Individual Researcher
UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors
Date pendingAtahan Cilan, Atay ÖzgövdeReinforcement Learning Human Behavior Simulation
Turkish Aerospace, Istanbul, Turkey · Department of Computer Engineering, Boğaziçi University, Istanbul, Turkey
Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning
Date pendingXuan Yu, Xu Wang, Rui Zhu +2Reinforcement Learning Generative Flow Networks
University of Science and Technology of China (USTC), Hefei, China · Suzhou Institute for Advanced Research, USTC, Suzhou, China · State Key Laboratory of Precision and Intelligent Chemistry, USTC, Hefei, China
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
Date pendingZikang Shan, Han Zhong, Liwei Wang +1RL for Language Models Reinforcement Learning
Peking University · Microsoft Research Asia · Shanghai Jiao Tong University
Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
Date pendingPhilip Jordan, Maryam KamgarpourNash Equilibrium Reinforcement Learning
SYCAMORE, EPFL
Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning
Date pendingAnthony GX-Chen, Ankit Anand, Gheorghe Comanici +7Reinforcement Learning RL for Language Model Reasoning
New York University · Google DeepMind

Date pending, cs.LGJ/K move · Enter open · S save

Safe Learning Under Irreversible Dynamics via Asking for Help

Benjamin Plaut, Juan Liévano-Karim, Hanlin Zhu, Stuart Russell

Division of Computer Science University of California Berkeley, CA 94720-1776, USA

Regret Minimization in RL Reinforcement Learning Safe RL

Open paper AskPDF arXiv

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that this combination enables the agent to learn both safely and effectively. Under standard online learning assumptions, we provide an algorithm whose regret and number of mentor queries are both sublinear in the time horizon for Markov decision processes with irreversible dynamics and infinite state spaces. Our proof involves a sequence of three reductions, making our result more general than a single algorithm. Conceptually, our result may be the first formal proof that it is possible for an agent to obtain high reward while becoming self-sufficient in an unknown, unbounded, and high-stakes environment without resets.

Momentum

Related topics

Latest papers 1,147