Codebase for the CausalWorld project conducted at the CORE Lab
-
Updated
Oct 31, 2025 - Python
#
causal-rl
Here are 3 public repositories matching this topic...
A compact causal-safety reinforcement learning benchmark for hidden-rule inference, sparse rewards, proxy traps, and alignment-gap measurement.
benchmark reinforcement-learning deep-reinforcement-learning q-learning dqn alignment gridworld gymnasium ai-safety pomdp double-dqn dueling-dqn intrinsic-motivation prioritized-experience-replay noisy-networks safe-rl reward-hacking causal-rl dqfd spie-q
-
Updated
Jun 17, 2026 - Python
Causal reinforcement learning, organized around Bareinboim's 9-task taxonomy — confounded offline→online RL, POMIS, counterfactual policies, transportability, discovery, imitation, curricula, shaping, games. Honest about scope. pip install causalrl
python reinforcement-learning pytorch sensitivity-analysis causal-inference gymnasium bandits counterfactual do-calculus causal-discovery off-policy-evaluation causal-reinforcement-learning causal-rl structural-causal-models transportability causal-bandits
-
Updated
Jun 19, 2026 - Python
Improve this page
Add a description, image, and links to the causal-rl topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the causal-rl topic, visit your repo's landing page and select "manage topics."