Maximum Entropy Dueling Network Architecture in Atari Domain

2021-07-30 · Alireza Nadali, Mohammad Mehdi Ebadzadeh

In recent years, there have been many deep structures for Reinforcement Learning, mainly for value function estimation and representations. These methods achieved great success in Atari 2600 domain. In this paper, we propose an improved architecture based upon Dueling Networks, in this architecture, there are two separate estimators, one approximate the state value function and the other, state advantage function. This improvement based on Maximum Entropy, shows better policy evaluation compared to the original network and other value-based architectures in Atari domain.

📄 PDF Abstract BibTeX arXiv:2107.14457

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning (RL)

Dueling Network Architectures for Deep Reinforcement Learning

2015-11-20 · Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt 외

In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-enc…

Atari Games Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Learning To Play Atari Games Using Dueling Q-Learning and Hebbian Plasticity

2024-05-22 · Md Ashfaq Salehin

In this work, an advanced deep reinforcement learning architecture is used to train neural network agents playing atari games. Given only the raw game pixels, action space, and reward information, the system can train ag…

Atari Games Deep Reinforcement Learning Lifelong learning Q-Learning

Sample Efficient Actor-Critic with Experience Replay

2016-11-03 · Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih 외

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atar…

continuous-control Continuous Control Deep Reinforcement Learning reinforcement-learning+2

DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic

2023-10-26 · Dexter Neo, Tsuhan Chen

We present a novel extension to the family of Soft Actor-Critic (SAC) algorithms. We argue that based on the Maximum Entropy Principle, discrete SAC can be further improved via additional statistical constraints derived …

Atari Games reinforcement-learning

Noisy Networks for Exploration

2017-06-30 · ICLR 2018 1 · Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick 외

We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameter…

Atari Games Deep Reinforcement Learning Efficient Exploration reinforcement-learning+2