20 results for “policy optimization”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper develops a new algorithm for policy optimization in online episodic tabular Markov decision processes with unknown transition kernels, providing data-dependent regret bounds and best-of-bot…
This paper proposes a new reinforcement learning algorithm called Forward Entropy-Regularized Policy Optimization (FERPO) that improves policies without differentiating the critic with respect to acti…
The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL…
This paper improves max-policy iteration by replacing mathematical optimization with value iteration and proposes min-policy iteration as an alternative to linear programming.
Yiming Ren, Yiran Xu, Zicheng Lin, Chufan Shi +7 more
The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…
This paper proposes Ordered Policy Optimization (OPO), a modification to Proximal Policy Optimization that adapts the clipping radius to the reliability of the induced importance ratio distribution.
The paper introduces Posterior Hybrid Bayesian Belief (PhyB), a novel framework that reformulates policy optimization in Bayesian Offline RL by approximating expectations as a convex combination over…
Johanna Menn, Miriam Kober, Paul Brunzema, David Stenger +1 more
The paper introduces local Preferential Bayesian Optimization (PBO) methods that adapt high-dimensional Bayesian Optimization techniques, such as trust-region and derivative-informed local search, to…
This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.
This paper provides non-asytotic sample complexity guarantees for the Navigate and Stop algorithm in online tabular Reinforcement Learning, identifying additional attributes that affect the overall sa…
This paper proposes Policy Gradient Steering (PGS), a new method for dynamically changing a large language model's behavior at inference time using reinforcement learning.
This paper introduces $k$-adaptable policy synthesis for optimizing a set of policies under uncertainty in Markov decision processes.
This paper studies the problem of learning an optimal policy and the action mask in a linear MDP model.
The paper introduces Safe Equilibrium Policy Optimization (σepo{}) to train language models for multi-agent strategic tasks, achieving improved safety and robustness across various game domains.
The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…
This paper introduces mean field reinforcement learning through Markov decision processes in large-population stochastic control, developing the necessary framework for representative-agent learning,…