Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rohan Paleja

Rohan Paleja

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2ML×2Robotics×1Multiagent×1

Frequent co-authors

Aarav G Sane2×
Karthik Sivachandran2×
Esmaeil Seraj1×
Luis Pimentel1×
Kin Man Lee1×
Zheyuan Wang1×

Research Timeline

2026
Differentiable Belief-based Opponent Shaping

The paper proposes D-BOS, a novel differentiable method that shapes opponent behavior by directly manipulating the opponent's inferred belief state, outperforming existing techniques in multi-agent games.

Differentiable Belief-based Opponent Shaping

The paper proposes D-BOS, a novel differentiable method that shapes opponent behavior by directly manipulating the opponent's inferred belief state, outperforming existing techniques in multi-agent games.

Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination

This paper extends Heterogeneous Policy Networks (HetNet) to support scaling heterogeneous robot teams and enables end-to-end training for learning highly efficient binarized messaging.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.MAEmpiricalRecentJun 18, 2026

Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination

Esmaeil Seraj, Rohan Paleja, Luis Pimentel, Kin Man Lee +6 more

This paper extends Heterogeneous Policy Networks (HetNet) to support scaling heterogeneous robot teams and enables end-to-end training for learning highly efficient binarized messaging.

View →
cs.AIcs.LGRecent
May 27, 2026

Differentiable Belief-based Opponent Shaping

Aarav G Sane, Karthik Sivachandran, Rohan Paleja

The paper proposes D-BOS, a novel differentiable method that shapes opponent behavior by directly manipulating the opponent's inferred belief state, outperforming existing techniques in multi-agent ga…

View →
cs.AIcs.LGRecentMay 27, 2026

Differentiable Belief-based Opponent Shaping

Aarav G Sane, Karthik Sivachandran, Rohan Paleja

The paper proposes D-BOS, a novel differentiable method that shapes opponent behavior by directly manipulating the opponent's inferred belief state, outperforming existing techniques in multi-agent ga…

View →