Proximal Curriculum with Task Correlations for Deep Reinforcement Learning

no code implementations • 3 May 2024 • Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla

a target distribution over complex tasks.

reinforcement-learning Reinforcement Learning (RL)

Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences

no code implementations • 4 Mar 2024 • Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Georgios Tzannetos, Goran Radanović, Adish Singla

Moreover, we extend our analysis to the approximate optimization setting and derive exponentially decaying convergence rates for both RLHF and DPO.

Learning Embeddings for Sequential Tasks Using Population of Agents

2 code implementations • 5 Jun 2023 • Mridul Mahajan, Georgios Tzannetos, Goran Radanovic, Adish Singla

We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning.

Decision Making

Neural Task Synthesis for Visual Programming

1 code implementation • 26 May 2023 • Victor-Alexandru Pădurean, Georgios Tzannetos, Adish Singla

Generative neural models hold great promise in enhancing programming education by synthesizing new content.

Imitation Learning

Proximal Curriculum for Reinforcement Learning Agents

1 code implementation • 25 Apr 2023 • Georgios Tzannetos, Bárbara Gomes Ribeiro, Parameswaran Kamalaruban, Adish Singla

We consider the problem of curriculum design for reinforcement learning (RL) agents in contextual multi-task settings.

reinforcement-learning Reinforcement Learning (RL)