Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection

About

Safe robot control requires maximizing return while satisfying safety constraints. In off-policy safe reinforcement learning, reward and safety Q-values are commonly learned by separate critic ensembles, with uncertainty handled independently for each objective. This objective-wise treatment neglects inter-objective correlation and can lead to overly conservative value estimates, thereby reducing sample efficiency. To address this issue, we propose Cholesky-Ordered Projection Q-learning (COP-Q), a safety-first method that incorporates inter-objective covariance into vector-valued Q-value estimation. COP-Q constructs a generalized confidence bound in the joint Q-value space and uses Cholesky factorization to encode objective priority in a sequential form. This preserves conservatism on safety while adaptively reducing excessive conservatism on the reward objective. The resulting estimate is used in both temporal-difference target computation and actor optimization. COP-Q incurs minimal computational overhead and is readily compatible with most existing deep Q-learning frameworks. Experiments on robot locomotion in Brax and safe navigation in Safety-Gymnasium, covering both hard- and soft-safety settings, demonstrate that COP-Q achieves strong safety performance together with competitive or improved sample efficiency relative to representative baselines.

Guopeng Li, Moritz A. Zanger, Matthijs T. J. Spaan, Julian F. P. Kooij• 2026

Related benchmarks

TaskDatasetResultRank
Robot LocomotionBrax Hopper hard-safety (test)
Number of Falls7
4
Robot LocomotionBrax Walker2d hard-safety (test)
Number of Falls13
4
Robot LocomotionBrax Humanoid hard-safety (test)
Number of Falls31
4
Robot LocomotionBrax Ant hard-safety (test)
Number of Falls23
4
Showing 4 of 4 rows

Other info

Follow for update