Reinforcement Learning
DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards
MetaCURL: Non-stationary Concave Utility Reinforcement Learning Bianca Marin Moreno Inria
We explore online learning in episodic Markov decision processes on non-stationary environments (changing losses and probability transitions).
Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization
Multi-task offline reinforcement learning aims to develop a unified policy for diverse tasks without requiring real-time interaction with the environment.
Diffuser Lite: Towards Real-time Diffusion Planning Zibin Dong 1 Jianye Hao
The capability of generating high-quality long-horizon trajectories makes it a promising research direction.
Robot Policy Learning with Temporal Optimal Transport Reward
Reward specification is one of the most tricky problems in Reinforcement Learning, which usually requires tedious hand engineering in practice.
Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning Tong Y ang
We further propose a federated natural actor critic (NAC) method for multi-task RL with function approximation and stochastic policy evaluation, and establish its finite-time sample complexity taking the errors of function approximation into account.
Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied
Full experimental details are provided in Appendix C.
Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs Kevin Tan, Wei Fan, Y uting Wei Department of Statistics and Data Science The Wharton School, University of Pennsylvania
Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022b) is whether hybrid RL can improve upon the existing lower bounds established for purely of-fline or online RL without requiring that the behavior policy visit every state and action the optimal policy does. While Li et al. (2023b) provided an affirmative answer for tabular P AC RL, the question remains unsettled for both the regret-minimizing and non-tabular cases. In this work, building upon recent advancements in offline RL and reward-agnostic exploration, we develop computationally efficient algorithms for both P AC and regret-minimizing RL with linear function approximation, without requiring concentrability on the entire state-action space. We demonstrate that these algorithms achieve sharper error or regret bounds that are no worse than, and can improve on, the optimal sample complexity in offline RL (the first algorithm, for P AC RL) and online RL (the second algorithm, for regret-minimizing RL) in linear Markov decision processes (MDPs), regardless of the quality of the behavior policy. To our knowledge, this work establishes the tightest theoretical guarantees currently available for hybrid RL in linear MDPs.