-
Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization
Action-constrained reinforcement learning (RL) is a widely-used approach...
02/22/2021 ∙ by Jyun-Li Lin, et al. ∙
0
∙
share
read it
-
Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification
Many real-world physical control systems are required to satisfy constra...
10/20/2020 ∙ by Daniel J. Mankowitz, et al. ∙
0
∙
share
read it
-
Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks
This paper focuses on finding reinforcement learning policies for contro...
03/20/2020 ∙ by Liyuan Zheng, et al. ∙
5
∙
share
read it
-
Constrained Upper Confidence Reinforcement Learning
Constrained Markov Decision Processes are a class of stochastic decision...
01/26/2020 ∙ by Liyuan Zheng, et al. ∙
0
∙
share
read it
-
Reinforcement Learning with Convex Constraints
In standard reinforcement learning (RL), a learning agent seeks to optim...
06/21/2019 ∙ by Sobhan Miryoosefi, et al. ∙
14
∙
share
read it
-
Verifiably Safe Off-Model Reinforcement Learning
The desire to use reinforcement learning in safety-critical settings has...
02/14/2019 ∙ by Nathan Fulton, et al. ∙
0
∙
share
read it
-
Automating Personnel Rostering by Learning Constraints Using Tensors
Many problems in operations research require that constraints be specifi...
05/29/2018 ∙ by Mohit Kumar, et al. ∙
0
∙
share
read it
Constrained episodic reinforcement learning in concave-convex and knapsack settings
06/09/2020 ∙ by Kianté Brantley, et al. ∙
8
∙
share
We propose an algorithm for tabular episodic reinforcement learning with constraints. We provide a modular analysis with strong theoretical guarantees for settings with concave rewards and convex constraints, and for settings with hard constraints (knapsacks). Most of the previous work in constrained reinforcement learning is limited to linear constraints, and the remaining work focuses on either the feasibility question or settings with a single episode. Our experiments demonstrate that the proposed algorithm significantly outperforms these approaches in existing constrained episodic environments.
READ FULL TEXT
Comments
There are no comments yet.