Skip to content

Latest commit

 

History

History
8 lines (7 loc) · 570 Bytes

README.md

File metadata and controls

8 lines (7 loc) · 570 Bytes

Meta Reinforcement Learning Experiments

  • async - just a plain Actor Critic
  • dqn - plain DQNetwork
  • fun - implementation of FeUdal Networks for Hierarchical Reinforcement Learning (https://arxiv.org/abs/1703.01161)
  • ga3c - implementation of GA3C: Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU (not finished)
  • meta_bandits - meta learning experiments using bandit environments (2 arms dependent, 2 arms independent and 11 arms)
  • meta_mdp - meta learning experiments using a simple MDP environment