conftrace_

finite mdp

3 papers

Explore in graph

Co-occurring keywords

markov decision process (790) episodic reinforcement learning (18) near-optimal policy (10) state similarity (6) mutual reinforcement (5) nonlinear optimization (28) linear convergence (158) optimal value (4) action similarity (2) policy iteration (99)

Papers

On the Linear Convergence of Policy Gradient Methods for Finite MDPs AISTATS 2021
Measuring Structural Similarities in Finite MDPs IJCAI 2019
Only H is left: Near-tight Episodic PAC RL NIPS 2016