Soft Actor-Critic for Discrete Action Settings

Code

• github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch
  OfficialIn paperpytorch★ 0
• github.com/ku2482/rljax
  jax★ 105
• github.com/lingweizhu/Pytorch-MunchausenActorCritic
  pytorch★ 4
• github.com/Epsilon10/MARL
  pytorch★ 4
• github.com/keraJLi/rejax
  jax★ 0
• github.com/ku2482/rltorch
  pytorch★ 0
• github.com/ac-93/soft-actor-critic
  tf★ 0
• github.com/ku2482/sac-discrete.pytorch
  pytorch★ 0
• github.com/Bigpig4396/PyTorch-Soft-Actor-Critic-SAC
  pytorch★ 0
• github.com/BY571/SAC_discrete
  pytorch★ 0

Abstract

Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve discrete actions, however, and so here we derive an alternative version of the Soft Actor-Critic algorithm that is applicable to discrete action settings. We then show that, even without any hyperparameter tuning, it is competitive with the tuned model-free state-of-the-art on a selection of games from the Atari suite.

Tasks

Benchmark Results

Reproductions