An empirical evaluation of interval estimation for Markov decision processes

2005 ◽  
Author(s):  
A.L. Strehl ◽  
M.L. Littman
Keyword(s):  
Markov Decision Processes ◽  
Empirical Evaluation ◽  
Interval Estimation ◽  
Decision Processes ◽  
Markov Decision

scholarly journals Simple Regret Optimization in Online Planning for Markov Decision Processes

2014 ◽  
Vol 51 ◽  
pp. 165-205 ◽  
Author(s):  
Z. Feldman ◽  
C. Domshlak
Keyword(s):  
Markov Decision Processes ◽  
State Of The Art ◽  
Search Algorithm ◽  
Empirical Evaluation ◽  
Decision Processes ◽  
Monte Carlo Tree Search ◽  
Performance Loss ◽  
Online Planning ◽  
Markov Decision ◽  
High Level

We consider online planning in Markov decision processes (MDPs). In online planning, the agent focuses on its current state only, deliberates about the set of possible policies from that state onwards and, when interrupted, uses the outcome of that exploratory deliberation to choose what action to perform next. Formally, the performance of algorithms for online planning is assessed in terms of simple regret, the agent's expected performance loss when the chosen action, rather than an optimal one, is followed. To date, state-of-the-art algorithms for online planning in general MDPs are either best effort, or guarantee only polynomial-rate reduction of simple regret over time. Here we introduce a new Monte-Carlo tree search algorithm, BRUE, that guarantees exponential-rate and smooth reduction of simple regret. At a high level, BRUE is based on a simple yet non-standard state-space sampling scheme, MCTS2e, in which different parts of each sample are dedicated to different exploratory objectives. We further extend BRUE with a variant of ``learning by forgetting.'' The resulting parametrized algorithm, BRUE(alpha), exhibits even more attractive formal guarantees than BRUE. Our empirical evaluation shows that both BRUE and its generalization, BRUE(alpha), are also very effective in practice and compare favorably to the state-of-the-art.

scholarly journals Enforcing Almost-Sure Reachability in POMDPs

2021 ◽  
pp. 602-625
Author(s):  
Sebastian Junges ◽  
Nils Jansen ◽  
Sanjit A. Seshia
Keyword(s):  
Markov Decision Processes ◽  
Empirical Evaluation ◽  
Decision Processes ◽  
Limited Information ◽  
Sequential Decision ◽  
Goal State ◽  
Learning Agent ◽  
Markov Decision ◽  
System Configurations ◽  
Partially Observable

AbstractPartially-Observable Markov Decision Processes (POMDPs) are a well-known stochastic model for sequential decision making under limited information. We consider the EXPTIME-hard problem of synthesising policies that almost-surely reach some goal state without ever visiting a bad state. In particular, we are interested in computing the winning region, that is, the set of system configurations from which a policy exists that satisfies the reachability specification. A direct application of such a winning region is the safe exploration of POMDPs by, for instance, restricting the behavior of a reinforcement learning agent to the region. We present two algorithms: A novel SAT-based iterative approach and a decision-diagram based alternative. The empirical evaluation demonstrates the feasibility and efficacy of the approaches.

scholarly journals Policy space identification in configurable environments

2021 ◽  
Author(s):  
Alberto Maria Metelli ◽  
Guglielmo Manneschi ◽  
Marcello Restelli
Keyword(s):  
Markov Decision Processes ◽  
Learning Process ◽  
Probabilistic Analysis ◽  
Exponential Family ◽  
Empirical Evaluation ◽  
Decision Processes ◽  
Statistical Testing ◽  
Policy Space ◽  
Markov Decision ◽  
Continuous Domains

AbstractWe study the problem of identifying the policy space available to an agent in a learning process, having access to a set of demonstrations generated by the agent playing the optimal policy in the considered space. We introduce an approach based on frequentist statistical testing to identify the set of policy parameters that the agent can control, within a larger parametric policy space. After presenting two identification rules (combinatorial and simplified), applicable under different assumptions on the policy space, we provide a probabilistic analysis of the simplified one in the case of linear policies belonging to the exponential family. To improve the performance of our identification rules, we make use of the recently introduced framework of the Configurable Markov Decision Processes, exploiting the opportunity of configuring the environment to induce the agent to reveal which parameters it can control. Finally, we provide an empirical evaluation, on both discrete and continuous domains, to prove the effectiveness of our identification rules.

Extreme-point solutions in Markov decision processes

1983 ◽  
Vol 20 (04) ◽  
pp. 835-842
Author(s):  
David Assaf
Keyword(s):  
Convex Function ◽  
Extreme Point ◽  
Markov Decision Processes ◽  
Convex Functions ◽  
Sufficient Conditions ◽  
Decision Processes ◽  
Markov Decision ◽  
Full Solution

The paper presents sufficient conditions for certain functions to be convex. Functions of this type often appear in Markov decision processes, where their maximum is the solution of the problem. Since a convex function takes its maximum at an extreme point, the conditions may greatly simplify a problem. In some cases a full solution may be obtained after the reduction is made. Some illustrative examples are discussed.

Sign in / Sign up

Export Citation Format

Share Document