-
Metrics for Markov Decision Processes with Infinite State Spaces
We present metrics for measuring state similarity in Markov decision pro...
07/04/2012 ∙ by Norman Ferns, et al. ∙
0
∙
share
read it
-
Provably Efficient Reinforcement Learning with Aggregated States
We establish that an optimistic variant of Q-learning applied to a finit...
12/13/2019 ∙ by Shi Dong, et al. ∙
0
∙
share
read it
-
Markov Decision Process for Video Generation
We identify two pathological cases of temporal inconsistencies in video ...
09/26/2019 ∙ by Vladyslav Yushchenko, et al. ∙
32
∙
share
read it
-
Metrics and continuity in reinforcement learning
In most practical applications of reinforcement learning, it is untenabl...
02/02/2021 ∙ by Charline Le Lan, et al. ∙
10
∙
share
read it
-
Scalable methods for computing state similarity in deterministic Markov Decision Processes
We present new algorithms for computing and approximating bisimulation m...
11/21/2019 ∙ by Pablo Samuel Castro, et al. ∙
49
∙
share
read it
-
Q-learning with Nearest Neighbors
We consider the problem of model-free reinforcement learning for infinit...
02/12/2018 ∙ by Devavrat Shah, et al. ∙
0
∙
share
read it
-
Blackwell Online Learning for Markov Decision Processes
This work provides a novel interpretation of Markov Decision Processes (...
12/28/2020 ∙ by Tao Li, et al. ∙
5
∙
share
read it
Metrics for Finite Markov Decision Processes
07/11/2012 ∙ by Norman Ferns, et al. ∙
0
∙
share
We present metrics for measuring the similarity of states in a finite Markov decision process (MDP). The formulation of our metrics is based on the notion of bisimulation for MDPs, with an aim towards solving discounted infinite horizon reinforcement learning tasks. Such metrics can be used to aggregate states, as well as to better structure other value function approximators (e.g., memory-based or nearest-neighbor approximators). We provide bounds that relate our metric distances to the optimal values of states in the given MDP.
READ FULL TEXT
Comments
There are no comments yet.