×
Feb 6, 2024 · This paper proposes to use inverse dynamic bisimulation metric for potential-based reward-shaping (PBRS). Specifically, the authors introduce the inverse ...
Specifically, we measure the novelty of adjacent states by calculating their distance using the bisimulation metric-based potential function, which enhances ...
Specifically, we propose a potential function based on the inverse dynamic bisimulation metric so that we can effectively explore the state space while ensuring ...
May 30, 2024 · Specifically, we measure the novelty of adjacent states by calculating their distance using the bisimulation metric-based potential function, ...
This is the official implementation of NeurIPS 2023 paper - [Efficient Potential-Based Exploration in Reinforcement Learning Using the Inverse Dynamic ...
Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric. 05:31 · Yiming Wang ; Uncertainty Estimation by Fisher ...
Nov 2, 2023 · Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric · YIMING WANG, Ming Yang, Renzhi ...
Efficient potential-based exploration in reinforcement learning using inverse dynamic bisimulation metric. Y Wang, M Yang, R Dong, B Sun, F Liu. Advances in ...
Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric, poster. Iteratively Learn Diverse Strategies with ...
People also ask
Efficient potential-based exploration in reinforcement learning using inverse dynamic bisimulation metric · Author Picture Yiming Wang.