Author name cluster

Kiran Ravish

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAMAS Conference 2026 Conference Paper

MA-SafeDiffuser: Safe Multi-Agent Planning with Diffusion Probabilistic Models

Kiran Ravish
Ankita Kushwaha
Preeti
Pawan Kumar

We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finitetime diffusion invariance guarantees for joint-agent safety specifications. Building on the single-agent construction that embeds control barrier function (CBF) constraints into reverse-diffusion updates, we: (i) formalize joint safe sets as intersections of peragent and pairwise barrier sets; (ii) derive centralized and decentralized (communication-aware) constrained denoising procedures with provable invariance under mild assumptions; (iii) address local-trap and deadlock phenomena via time-varying specifications and liveness CBFs; and (iv) develop a lightweight benchmarking suite including a multi-agent Maze2D domain. Empirically, MA- SafeDiffuser reduces violation counts relative to unconstrained diffusion baselines, while retaining planning quality. We provide algorithms, proofs, and reference implementations.

PDF

AAMAS Conference 2026 Conference Paper

Safe Offline Reinforcement Learning using Diffusion Policies

Ankita Kushwaha
Kiran Ravish
Preeti
Pawan Kumar
Anuj Mahajan

DiffusionmodelshaveshowngreatpromiseforofflineRLbycapturing complex data distributions, yet their standard formulations lack explicit safety mechanisms. We propose Safe Diffusion Q-learning, which extends Diffusion-QL by integrating a cost critic and a direct penalty term into the diffusion policy objective to enforce constraint satisfaction during action generation. Evaluated on the DSRL benchmark, our method achieves near-zero constraint violation on challenging BulletSafetyGym and SafetyGym tasks while maintainingcompetitiverewardperformance. Theseresultsdemonstrate that expressive diffusion policies can be robustly constrained, enabling their use in safety-critical offline RL.

PDF