Overview¶

MORL-Baselines contains multiple implementations of multi-objective reinforcement learning algorithms. The following table lists the algorithms that are currently implemented in MORL-Baselines.

Name	Single/Multi-policy	ESR/SER	Observation space	Action space	Paper
GPI-LS + GPI-PD	Multi	SER	Continuous	Discrete / Continuous	Paper and Supplementary Materials
MORL/D	Multi	/	/	/	Paper
Envelope Q-Learning	Multi	SER	Continuous	Discrete	Paper
CAPQL	Multi	SER	Continuous	Continuous	Paper
PGMORL ¹	Multi	SER	Continuous	Continuous	Paper / Supplementary Materials
Pareto Conditioned Networks (PCN)	Multi	SER/ESR ²	Continuous	Discrete / Continuous	Paper
Pareto Q-Learning	Multi	SER	Discrete	Discrete	Paper
MO Q learning	Single	SER	Discrete	Discrete	Paper
MPMOQLearning (outer loop MOQL)	Multi	SER	Discrete	Discrete	Paper
Optimistic Linear Support (OLS)	Multi	SER	/	/	Section 3.3 of the thesis
Expected Utility Policy Gradient (EUPG)	Single	ESR	Discrete	Discrete	Paper

:warning: Some of the algorithms have limited features.

1: Currently, PGMORL is limited to environments with 2 objectives.

2: PCN assumes environments with deterministic transitions.