Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping
This work addresses computational efficiency for researchers and practitioners in inverse reinforcement learning, but it is incremental as it builds on existing reward shaping techniques.
The paper tackles the computational challenge in inverse reinforcement learning by proposing the use of potential-based reward shaping to reduce the burden of reinforcement learning sub-problems, serving as a proof-of-concept to inspire future efficient methods.
Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce the computational burden of each RL sub-problem. This work serves as a proof-of-concept and we hope will inspire future developments towards computationally efficient IRL.