Skip to content

Collection of codes pertaining to my research in model-free RL algorithms.

License

Notifications You must be signed in to change notification settings

cbanerji/Sample_efficient_RL.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RL_research :

-- About : Mainly focusses on augmenting sample efficiency in conventional RL algorithms and designing of new ones, using novel techniques based on deep generative models, optimization, machine learning techniques etc.

  • sac_ipns -- Implements a novel intrinsic reward generation technique termed IPNS, augmenting exploration of Soft actor critic (SAC) algorithm and improving its performance.
  • ddpg_td3_ipns -- Pairing of IPNS artifacts with conventional DDPG and TD3 algorithms.
  • sac_isac -- implementation of my work named ISAC: Improved Soft Actor-Critic, a later version of the shared code was used to generate the plots in the paper. In our proposed improved SAC (ISAC), we first introduce a new prioritization scheme for selecting better samples from the experience replay (ER) buffer. Second we use a mixture of the prioritized off-policy data with the latest on-policy data for training the policy and value function networks.

About

Collection of codes pertaining to my research in model-free RL algorithms.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages