Dueling Network Architectures for Deep Reinforcement Learning

Code

• github.com/labmlai/annotated_deep_learning_paper_implementations
  pytorch★ 66,103
• github.com/facebookresearch/ReAgent
  pytorch★ 3,690
• github.com/facebookresearch/Horizon
  pytorch★ 3,686
• github.com/opendilab/DI-engine
  pytorch★ 3,606
• github.com/tensorlayer/RLzoo
  tf★ 644
• github.com/wtingda/DeepRLBreakout
  tf★ 6
• github.com/xusophia/DataSciFinalProj
  pytorch★ 4
• github.com/prajwalgatti/DRL-Continuous-Control
  none★ 1
• github.com/la3lma/Chez
  tf★ 1
• github.com/la3lma/chezjulia
  tf★ 1

Abstract

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-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying reinforcement learning algorithm. Our results show that this architecture leads to better policy evaluation in the presence of many similar-valued actions. Moreover, the dueling architecture enables our RL agent to outperform the state-of-the-art on the Atari 2600 domain.

Tasks

Benchmark Results

Reproductions