Dibya Ghosh

16 papers · 2018–2025 · 5 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🐝 Cross-Pollinator (14) 🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🌈 Renaissance Researcher (5)

🌍 Conference Polyglot (5) 🏃 Academic Marathon (7) 🌈 Renaissance Researcher (5) 🤝 Dynamic Duo (14) 👥 Mega-Team (35) 🔥 Unstoppable (8) 💎 Century Club (16) 🚀 Conference Pioneer 🗃️ Keyword Collector (51) ❓ The Questioner

Conferences

NIPS (6) ICLR (4) ICML (4) CORL (1) RSS (1)

Top co-authors

Sergey Levine (14) Abhishek Gupta (3) Aviral Kumar (3) Benjamin Eysenbach (2) Karl Pertsch (2) Chelsea Finn (2) Justin Fu (2) Anurag Ajay (2) Pulkit Agrawal (2) Quan Vuong (2)

Keywords

representation learning (3) offline reinforcement learning (2) reinforcement learning (2) imitation learning (1) function approximation (1) policy optimization (1) bayesian inference (1) variational inference (1) distribution shift (1) policy gradient (1) policy iteration (1) epistemic uncertainty (1) inverse reinforcement learning (1) hierarchical reinforcement learning (1) partially observable markov decision process (1) domain generalization (1) continuous control (1) reward function (1) temporal difference learning (1) deep reinforcement learning (1)

Papers

$\pi_0.5$: a Vision-Language-Action Model with Open-World Generalization CORL 2025 What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning? ICML 2025 Octo: An Open-Source Generalist Robot Policy RSS 2024 Reinforcement Learning from Passive Data via Latent Intentions ICML 2023 HIQL: Offline Goal-Conditioned RL with Latent States as Actions NIPS 2023 Accelerating Exploration with Unlabeled Prior Data NIPS 2023 Distributionally Adaptive Meta Reinforcement Learning NIPS 2022 Offline RL Policies Should Be Trained to be Adaptive ICML 2022 Learning to Reach Goals via Iterated Supervised Learning ICLR 2021 Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning ICLR 2021 Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability NIPS 2021 Representations for Stable Off-Policy Reinforcement Learning ICML 2020 An operator view of policy gradient methods NIPS 2020 Learning Actionable Representations with Goal Conditioned Policies ICLR 2019 Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition NIPS 2018 Divide-and-Conquer Reinforcement Learning ICLR 2018