Search Results for author:
Found 4 papers, 2 papers with code
Leveraging Domain-Unlabeled Data in Offline Reinforcement Learning across Two Domains
In this paper, we investigate an offline reinforcement learning (RL) problem where datasets are collected from two domains.
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
We study a primal-dual reinforcement learning (RL) algorithm for the online constrained Markov decision processes (CMDP) problem, wherein the agent explores an optimal policy that maximizes return while satisfying constraints.
End-to-End Policy Gradient Method for POMDPs and Explainable Agents
We proposed an RL algorithm that estimates the hidden states by end-to-end training, and visualize the estimation as a state-transition graph.
Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning
We propose Pgx, a suite of board game reinforcement learning (RL) environments written in JAX and optimized for GPU/TPU accelerators.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
