conftrace_

continuous mdp

4 papers

Explore in graph

Co-occurring keywords

regret bound (1926) local linearity (4) non-parametric estimation (23) kernel methods (1097) non-markovian policy (3) occupancy measure (12) measure theory (5) kernel ucbvi (1) deep reactive policies (2) iterative lower bound optimization (1)

Papers

Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs NIPS 2024
On the Occupancy Measure of Non-Markovian Policies in Continuous MDPs ICML 2023
Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs AAAI 2022
Kernel-Based Reinforcement Learning: A Finite-Time Analysis ICML 2021