Reinforcement Learning
Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
We provide both theoretical analysis and experimental results to validate the effectiveness of our proposed algorithm.
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning David Y unis TTI-Chicago Chicago, IL
Exploration in sparse-reward reinforcement learning (RL) is difficult due to the need for long, coordinated sequences of actions in order to achieve any reward.
Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making Ting Li
A/B testing is critical for modern technological companies to evaluate the effectiveness of newly developed products against standard baselines. This paper studies optimal designs that aim to maximize the amount of information obtained from online experiments to estimate treatment effects accurately.
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies.
Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
To this end, we introduce Poppy, a simple training procedure for populations.