Bounding the Optimal Value Function in Compositional Reinforcement Learning

1 code implementation • 5 Mar 2023 • Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas, Stas Tiomkin, Rahul V. Kulkarni

In order to quickly obtain solutions to unseen problems with new reward functions, a popular approach involves functional composition of previously solved tasks.

reinforcement-learning Reinforcement Learning (RL)

Compositionality and Bounds for Optimal Value Functions in Reinforcement Learning

no code implementations • 19 Feb 2023 • Jacob Adamczyk, Stas Tiomkin, Rahul Kulkarni

An agent's ability to reuse solutions to previously solved problems is critical for learning new tasks efficiently.

reinforcement-learning Reinforcement Learning (RL)

Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning

no code implementations • 2 Dec 2022 • Jacob Adamczyk, Argenis Arriojas, Stas Tiomkin, Rahul V. Kulkarni

In this work, we develop a general framework for reward shaping and task composition in entropy-regularized RL.

reinforcement-learning Reinforcement Learning (RL) +1

Entropy Regularized Reinforcement Learning Using Large Deviation Theory

2 code implementations • 7 Jun 2021 • Argenis Arriojas, Jacob Adamczyk, Stas Tiomkin, Rahul V. Kulkarni

The mapping established in this work connects current research in reinforcement learning and non-equilibrium statistical mechanics, thereby opening new avenues for the application of analytical and computational approaches from one field to cutting-edge problems in the other.

reinforcement-learning Reinforcement Learning (RL)

Neural Network Degeneration and its Relationship to the Brain

no code implementations • 31 Jul 2020 • Jacob Adamczyk

This report discusses the application of neural networks (NNs) as small segments of the brain.