Sorry, you need to enable JavaScript to visit this website.

Attention based Curiosity-driven Exploration in Deep Reinforcement Learning

Primary tabs

Citation Author(s):
Patrik Reizinger, Márton Szemenyei
Submitted by:
Patrik Reizinger
Last updated:
17 May 2020 - 3:59pm
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters Name:
Patrik Reizinger
Paper Code:
MLSP-P3.3

Abstract 

Abstract: 

Reinforcement Learning enables to train an agent via interaction with the environment. However, in the majority of real-world scenarios, the extrinsic feedback is sparse or not sufficient, thus intrinsic reward formulations are needed to successfully train the agent. This work investigates and extends the paradigm of curiosity-driven exploration. First, a probabilistic approach is taken to exploit the advantages of the attention mechanism, which is successfully applied in other domains of Deep Learning. Combining them, we propose new methods, such as AttA2C, an extension of the Actor-Critic framework. Second, another curiosity-based approach - ICM - is extended. The proposed model utilizes attention to emphasize features for the dynamic models within ICM, moreover, we also modify the loss function, resulting in a new curiosity formulation, which we call rational curiosity. The corresponding implementation can be found at https://github.com/rpatrik96/AttA2C/

up
0 users have voted:

Dataset Files

ICASSP_presentation.pdf

(142)