In this paper, we present an online reinforcement learning algorithm, called Renewal Monte Carlo (RMC), for infinite horizon Markov decision processes with a designated start state. RMC is a Monte Carlo algorithm and retains the advantages of Monte Carlo methods including low bias, simplicity, and ease of implementation while, at the same time, circumvents their key drawbacks of high variance a...

Turn-based stochastic games and its important subclass Markov decision processes (MDPs) provide models for systems with both probabilistic and nondeterministic behaviors. We consider turnbased stochastic games with two classical quantitative objectives: discounted-sum and long-run average objectives. The game models and the quantitative objectives are widely used in probabilistic verification, ...

In this paper, we propose a model of intertemporal choice that explicitly incorporates satiation due to previous consumption in the evaluation of the utility of current consumption. In the discounted utility (DU) model, the utility of consumption is evaluated afresh in each time period. In our model, the utility of current consumption represents an incremental utility from the past level. When ...

We give an alternative proof to a result of Mertens and Parthasarathy, stating that every n-player discounted stochastic game with general setup, and with a norm-continuous transition, has a subgame perfect equilibrium. † Institute of Mathematics and Center for Rationality and Interactive Decision Theory, The Hebrew University, Givat Ram, 91904 Jerusalem, Israel. e-mail: [email protected] ...

Recurrent Neural Networks architectures excel at processing sequences by modelling dependencies over different timescales. The recently introduced Recurrent Weighted Average (RWA) unit captures long term dependencies far better than an LSTM on several challenging tasks. The RWA achieves this by applying attention to each input and computing a weighted average over the full history of its comput...