Implementation HindSight Experience Replay algorithm with DDPG and Soft Actor Critic Algorithm and testing it on pybullet gym environments.
HindSightExperience replay paper.
There are implementation of DQN and testing it with HER on BitFlipEnvironment.
Also there is implementation of DDPG and SoftActorCritic Algorithms which are tested on FetchPush-v2 environment from gymnasium-robotics.
All notebooks with experiments are in directory experiments All based RL algoritms (DQN, SAC, DDPG) are in directory models