Conservative Exploration in Reinforcement Learning

by   Evrard Garcelon, et al.

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will eventually learn a good or optimal policy, there is no guarantee on the quality of the intermediate policies. This lack of control is undesired in real-world applications where a minimum requirement is that the executed policies are guaranteed to perform at least as well as an existing baseline. In this paper, we introduce the notion of conservative exploration for average reward and finite horizon problems. We present two optimistic algorithms that guarantee (w.h.p.) that the conservative constraint is never violated during learning. We derive regret bounds showing that being conservative does not hinder the learning ability of these algorithms.


page 1

page 2

page 3

page 4


Exploration-Exploitation in Constrained MDPs

In many sequential decision-making problems, the goal is to optimize a u...

Conservative Optimistic Policy Optimization via Multiple Importance Sampling

Reinforcement Learning (RL) has been able to solve hard problems such as...

Revisiting Peng's Q(λ) for Modern Reinforcement Learning

Off-policy multi-step reinforcement learning algorithms consist of conse...

Improved Algorithms for Conservative Exploration in Bandits

In many fields such as digital marketing, healthcare, finance, and robot...

Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process

We tackle the problem of acting in an unknown finite and discrete Markov...

Receding Horizon Curiosity

Sample-efficient exploration is crucial not only for discovering rewardi...

Knowledge is reward: Learning optimal exploration by predictive reward cashing

There is a strong link between the general concept of intelligence and t...