23 citations · 101 across the 30 of their papers we have counts for
14 papers · 1 filter
Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos
Tristan Shah, Wooyoung Chung, Volodomyr Makarenko +2
Reinforcement learning (RL) is a powerful paradigm for training agents, yet its success rests on domain expertise of human engineers who design informative reward signals for every…
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…
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…
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…
Boosting Soft Q-Learning by Bounding
Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin +1
An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approxima…
Bounding the Optimal Value Function in Compositional Reinforcement Learning
Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas +2
In the field of reinforcement learning (RL), agents are often tasked with solving a variety of problems differing only in their reward functions. In order to quickly obtain solutio…
Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function
Jacob Adamczyk, Stas Tiomkin, Rahul Kulkarni
An agent's ability to leverage past experience is critical for efficiently solving new tasks. Approximate solutions for new tasks can be obtained from previously derived value func…
Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning
Jacob Adamczyk, Argenis Arriojas, Stas Tiomkin +1
In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved tasks can allow agents to quickly solve new problems. In some cases, these new problem…
Entropy Regularized Reinforcement Learning Using Large Deviation Theory
Argenis Arriojas, Jacob Adamczyk, Stas Tiomkin +1
Reinforcement learning (RL) is an important field of research in machine learning that is increasingly being applied to complex optimization problems in physics. In parallel, conce…
Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning
Xingyu Lu, Kimin Lee, Pieter Abbeel +1
Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle t…
Efficient Empowerment Estimation for Unsupervised Stabilization
Ruihan Zhao, Kevin Lu, Pieter Abbeel +1
Intrinsically motivated artificial agents learn advantageous behavior without externally-provided rewards. Previously, it was shown that maximizing mutual information between agent…
Preventing Imitation Learning with Adversarial Policy Ensembles
Albert Zhan, Stas Tiomkin, Pieter Abbeel
Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. Policies, such as human, or policies on deployed robots, can all be…
Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards
Xingyu Lu, Stas Tiomkin, Pieter Abbeel
While recent progress in deep reinforcement learning has enabled robots to learn complex behaviors, tasks with long horizons and sparse rewards remain an ongoing challenge. In this…
Learning Efficient Representation for Intrinsic Motivation
Ruihan Zhao, Stas Tiomkin, Pieter Abbeel
Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS ca…