Advances in Reinforcement Learning

The field of reinforcement learning is moving towards more robust and generalizable methods, with a focus on addressing challenges such as sparse reward signals, high-dimensional state spaces, and unwanted actions. Recent developments have introduced innovative approaches, including object-centric attention, penalty-based bidirectional learning, and time-weighted contrastive reward learning, which have shown significant improvements in performance and efficiency. Notable papers in this area include:

  • Deep Reinforcement Learning via Object-Centric Attention, which introduced OCCAM, a method that selectively preserves task-relevant entities while filtering out irrelevant visual information.
  • TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning, which proposed a framework that leverages both successful and failed demonstrations to learn a dense reward function.
  • MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning, which presented a new algorithm to resolve information conflicts for visual MBRL, resulting in more robust policies.
  • Momentum Boosted Episodic Memory for Improving Learning in Long-Tailed RL Environments, which proposed an architecture for learning from Zipfian distributions, yielding improved performance in multiple tasks.

Sources

Deep Reinforcement Learning via Object-Centric Attention

Enhanced Penalty-based Bidirectional Reinforcement Learning Algorithms

MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning

TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning

Momentum Boosted Episodic Memory for Improving Learning in Long-Tailed RL Environments

Free Random Projection for In-Context Reinforcement Learning

Are We Done with Object-Centric Learning?

Built with on top of