paper-with-me

Papers

Extrapolation in Gridworld Markov-Decision Processes

2020-04-14 · Eugene Charniak

Extrapolation in reinforcement learning is the ability to generalize at test time given states that could never have occurred at training time. Here we consider four factors that lead to improved extrapolation in a simple Gridworld environment: (a) avoiding maximum Q-value (or other deterministic methods) for action choice at test time, (b) ego-centric representation of the Gridworld, (c) building rotational and mirror symmetry into the learning mechanism using rotational and mirror invariant convolution (rather than standard translation-invariant convolution), and (d) adding a maximum entropy term to the loss function to encourage equally good actions to be chosen equally often.

📄 PDF Abstract BibTeX arXiv:2004.06784

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Translation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Contingency Planning Using Bi-level Markov Decision Processes for Space Missions

2024-02-26 · Somrita Banerjee, Edward Balaban, Mark Shirley, Kevin Bradner 외

This work focuses on autonomous contingency planning for scientific missions by enabling rapid policy computation from any off-nominal point in the state space in the event of a delay or deviation from the nominal missio…

Decision Making

Detecting Spiky Corruption in Markov Decision Processes

2019-06-30 · Jason Mancuso, Tomasz Kisielewski, David Lindner, Alok Singh

Current reinforcement learning methods fail if the reward function is imperfect, i.e. if the agent observes reward different from what it actually receives. We study this problem within the formalism of Corrupt Reward Ma…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Learning Mixtures of Markov Chains and MDPs

2022-11-17 · Chinmaya Kausik, Kevin Tan, Ambuj Tewari

We present an algorithm for learning mixtures of Markov chains and Markov decision processes (MDPs) from short unlabeled trajectories. Specifically, our method handles mixtures of Markov chains with optional control inpu…

Self-Triggered Markov Decision Processes

2021-02-17 · Yunhan Huang, Quanyan Zhu

In this paper, we study Markov Decision Processes (MDPs) with self-triggered strategies, where the idea of self-triggered control is extended to more generic MDP models. This extension broadens the application of self-tr…

Learning Markov State Abstractions for Deep Reinforcement Learning

2021-06-08 · NeurIPS 2021 12 · Cameron Allen, Neev Parikh, Omer Gottesman, George Konidaris

A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way o…

continuous-controlContinuous ControlContrastive LearningDeep Reinforcement Learning+3