- Environment Farming
- Dinamic allocation of Eval_Sampler(environment for it) - FIXED
- Environment allocation bugs - FIXED
- Segmentation fault - FIXED
Reinforcement learning framework and algorithms implemented in PyTorch.
Some implemented algorithms:
- Temporal Difference Models (TDMs)
- Deep Deterministic Policy Gradient (DDPG)
- (Double) Deep Q-Network (DQN)
- Soft Actor Critic (SAC)
- Twin Dueling Deep Determinstic Policy Gradient (TD3)
To get started, checkout the example scripts, linked above.
Install and use the included ananconda environment
$ conda env create -f rlkit-env.yml
$ source activate rlkit-env
A lot of the coding infrastructure is based on rllab. The serialization and logger code are basically a carbon copy of the rllab versions.