Temporal Regularization for Markov Decision Process
Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularization techniques focus on spatial (perceptual) regularization. Yet in reinforcement learning, due to the nature of the Bellman equation, there is an opportunity to also exploit temporal regularization based on smoothness in value estimates over trajectories. This paper explores a class of methods for temporal regularization. We formally characterize the bias induced by this technique using Markov chain concepts. We illustrate the various characteristics of temporal regularization via a sequence of simple discrete and continuous MDPs, and show that the technique provides improvement even in high-dimensional Atari games.
Code (1)
Tasks
Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Temporal Regularization in Markov Decision Process
Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to re…
Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes
We study the error introduced by entropy regularization in infinite-horizon, discrete, discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength both in …
Policy Gradient MethodsRegular Decision Processes for Grid Worlds
Markov decision processes are typically used for sequential decision making under uncertainty. For many aspects however, ranging from constrained or safe specifications to various kinds of temporal (non-Markovian) depend…
Decision MakingDecision Making Under UncertaintyIncremental LearningSequential Decision MakingSparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning
In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Bayesian regularization of empirical MDPs
In most applications of model-based Markov decision processes, the parameters for the unknown underlying model are often estimated from the empirical data. Due to noise, the policy learnedfrom the estimated model is ofte…