causalrl
Causal reinforcement learning, organized around Bareinboim's 9-task taxonomy, confounded offline→online RL, POMIS, counterfactual policies, transportability, discovery, imitation, curricula.
View on Github
Activity
- Latest release
- 1mo ago
- Total releases
- 16
- Cadence
- ~daily
- Last 12 months
- 16
Reach
- Stars
- 0
Details
- License
- MIT
- First release
- May 29, 2026
Releases
| Version | Released | |
|---|---|---|
3.0.0
major
| ||
2.1.0
minor
| ||
2.0.0
major
| ||
1.7.0
minor
| ||
1.6.0
minor
| ||
1.5.0
minor
| ||
1.4.0
minor
| ||
1.3.0
minor
| ||
1.2.0
minor
| ||
1.0.0
major
| ||
0.99.7
patch
| ||
0.99.6
patch
| ||
0.99.5
patch
| ||
0.99.4
patch
| ||
0.99.3
patch
| ||
0.99.2
initial
|