7 papers
Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learning
Meraj Mammadov, Pedro Zuidberg Dos Martires, Johannes Andreas Stork
Imitation learning (IL) from a state-based reinforcement learning (RL) policy is a common approach to overcome the curse of dimensionality in complex and high-dimensional observati…
Progress Constraints for Reinforcement Learning in Behavior Trees
Finn Rietz, Mart KartaÅ¡ev, Petter Ãgren +1
Behavior Trees (BTs) provide a structured and reactive framework for decision-making, commonly used to switch between sub-controllers based on environmental conditions. Reinforceme…
APC-RL: Exceeding Data-Driven Behavior Priors with Adaptive Policy Composition
Finn Rietz, Pedro Zuidberg dos Martires, Johannes Andreas Stork
Incorporating demonstration data into reinforcement learning (RL) can greatly accelerate learning, but existing approaches often assume demonstrations are optimal and fully aligned…
Trajectory prediction for heterogeneous agents: A performance analysis on small and imbalanced datasets
Tiago Rodrigues de Almeida, Yufei Zhu, Andrey Rudenko +4
Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently…
KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies
Shih-Min Yang, Martin Magnusson, Johannes A. Stork +1
Soft Actor-Critic (SAC) has achieved notable success in continuous control tasks but struggles in sparse reward settings, where infrequent rewards make efficient exploration challe…
On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learning
Marco Iannotta, Johannes A. Stork, Erik Schaffernicht +1
With the rising demand for flexible manufacturing, robots are increasingly expected to operate in dynamic environments where local -- such as slight offsets or size differences in…