7 papers
Maximum Entropy Exploration Without the Rollouts
Jacob Adamczyk, Adam Kamoski, Rahul V. Kulkarni
Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective for data collection, particularly when an external reward fun…
Thermodynamics of Reinforcement Learning Curricula
Jacob Adamczyk, Juan Sebastian Rojas, Rahul V. Kulkarni
Connections between statistical mechanics and machine learning have repeatedly proven fruitful, providing insight into optimization, generalization, and representation learning. In…
Average-Reward Soft Actor-Critic
Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin +1
The average-reward formulation of reinforcement learning (RL) has drawn increased interest in recent years for its ability to solve temporally-extended problems without relying on…
Exploration Behavior of Untrained Policies
Jacob Adamczyk
Exploration remains a fundamental challenge in reinforcement learning (RL), particularly in environments with sparse or adversarial reward structures. In this work, we study how th…
Bootstrapped Reward Shaping
Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin +1
In reinforcement learning, especially in sparse-reward domains, many environment steps are required to observe reward information. In order to increase the frequency of such observ…
EVAL: EigenVector-based Average-reward Learning
Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin +1
In reinforcement learning, two objective functions have been developed extensively in the literature: discounted and averaged rewards. The generalization to an entropy-regularized…