Implemented Algorithms
Contents
Implemented Algorithms#
robomimic includes several high-quality implementations of offline learning algorithms, and offers tools to easily build your own learning algorithms.
Imitation Learning#
BC#
Vanilla Behavioral Cloning (see this paper), consisting of simple supervised regression from observations to actions. Implemented in the
BC
class inalgo/bc.py
, along with some variants such asBC_GMM
(stochastic GMM policy) andBC_VAE
(stochastic VAE policy)
BC-RNN#
Behavioral Cloning with an RNN network. Implemented in the
BC_RNN
andBC_RNN_GMM
(recurrent GMM policy) classes inalgo/bc.py
.
BC-Transformer#
Behavioral Cloning with an Transformer network. Implemented in the
BC_Transformer
andBC_Transformer_GMM
(transformer GMM policy) classes inalgo/bc.py
.
HBC#
Hierarchical Behavioral Cloning - the implementation is largely based off of this paper. Implemented in the
HBC
class inalgo/hbc.py
.
Offline Reinforcement Learning#
IRIS#
A recent batch offline RL algorithm from this paper. Implemented in the
IRIS
class inalgo/iris.py
.
BCQ#
A recent batch offline RL algorithm from this paper. Implemented in the
BCQ
class inalgo/bcq.py
.
CQL#
A recent batch offline RL algorithm from this paper. Implemented in the
CQL
class inalgo/cql.py
.
IQL#
A recent batch offline RL algorithm from this paper. Implemented in the
IQL
class inalgo/iql.py
.
TD3-BC#
A recent algorithm from this paper. We implemented it as an example (see section below on building your own algorithm). Implemented in the
TD3_BC
class inalgo/td3_bc.py
.