On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “POLITEX”

Exploration-Enhanced POLITEXcs.LG

Enhances POLITEX for exploration in reinforcement learning with no-reward learning.

problem Learning to explore in reinforcement learning problems with no-reward.

method Modifies POLITEX to incorporate a pre-existing exploration policy.

result Achieves sublinear regret guarantees similar to POLITEX but without requiring all policies to explore.

reinforcement learning exploration POLITEX no-reward learning average-cost

2019-08-27abs ↗pdf ↗

Improved Regret Bound and Experience Replay in Regularized Policy Iterationcs.LG

Improved Politex algorithm reduces regret bound to O(√T) with experience replay.

problem Learning in infinite-horizon MDPs with function approximation.

method Sharpened regret analysis of Politex algorithm, experience replay implementation.

result First high-probability O(√T) regret bound for computationally efficient algorithm.

regret bound policy iteration experience replay Markov decision processes function approximation

2021-02-25abs ↗pdf ↗

Efficient Local Planning with Linear Function Approximationcs.LG

Efficient local planning with linear approximations for agents with limited simulator access.

problem Planning with limited simulator access in reinforcement learning.

method Confident Monte Carlo Least Square Policy Iteration (Confident MC-LSPI) and Politex (Confident MC-Politex) algorithms.

result The algorithms can learn the optimal policy with local simulator access, even for linear Q-functions.

reinforcement learning local planning linear function approximation simulator access policy iteration

2021-08-12abs ↗pdf ↗

On Connections between Constrained Optimization and Reinforcement Learningcs.LG

Paper connects DP and optimization for RL, suggesting new algorithms.

problem Optimizing scalar objectives in RL.

method Drawing connections between DP and optimization algorithms.

result Links between DP schemes and optimization algorithms.

Reinforcement Learning Dynamic Programming Convex Optimization Frank-Wolfe Mirror Descent

2019-10-18abs ↗pdf ↗