chandar-lab's repositories
Recall2Imagine
Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024
Lifelong-Hanabi
A Continual Multi-agent RL testbed based on Hanabi
CriticalGradientOptimization
Critical Gradient Optimization.
healthy-data-diet
Reduce gender bias in machine learning models.
tgi-for-mila
A toolkit for running text-generation-inference on Mila and Compute Canada
crystal-design
Reinforcement Learning for Crystal Structure Design
SubGoal_Distillation_LLM
Code for the paper Sub-goal Distillation: A Method to Improve Small Language Agents
Language:Jupyter Notebook000
Lookbehind-SAM
Implementation of Lookbehind-SAM: k steps back, 1 step forward (ICML 2024)
Language:PythonApache-2.0000
Language:JavaScript000
Language:PythonMIT000