Reinforcement Learning of POMDPs using Spectral Methods
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the future observations in the process. We devise a learning algorithm running through episodes, in each episode we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fixed policy. At the end of the episode, an optimization oracle returns the optimal memoryless planning policy which maximizes the expected reward based on the estimated POMDP model. We prove an order-optimal regret bound with respect to the optimal memoryless policy and efficient scaling with respect to the dimensionality of observation and action spaces.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Experimental results : Reinforcement Learning of POMDPs using Spectral Methods
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent le…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Sublinear Regret for Learning POMDPs
We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the POMDP with a known environment in terms of the…
reinforcement-learningReinforcement Learning (RL)Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning
Solving partially observable Markov decision processes (POMDPs) requires computing policies under imperfect state information. Despite recent advances, the scalability of existing POMDP solvers remains limited. Moreover,…
Reinforcement LearningFuture-Dependent Value-Based Off-Policy Evaluation in POMDPs
We study off-policy evaluation (OPE) for partially observable MDPs (POMDPs) with general function approximation. Existing methods such as sequential importance sampling estimators and fitted-Q evaluation suffer from the …
Off-policy evaluationSample-Efficient Reinforcement Learning of Undercomplete POMDPs
Partial observability is a common challenge in many reinforcement learning applications, which requires an agent to maintain memory, infer latent states, and integrate this past information into exploration. This challen…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)