Offline-to-online is a key strategy for advancing reinforcement learning towards practical applications. This approach not only reduces the risks and costs associated with online exploration, but also accelerates the agent’s adaptation to real-world environments. It consists of two phases: offline-training and fine-tuning. However, offline-training and fine-tuning have different problems. In offline-training, the main difficulty is how to learn an excellent policy in a limited and incompletely distributed dataset.

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Subscribe now or login.

[1] yesen chen, "EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning ", IEEE Dataport, 2024. [Online]. Available: http://dx.doi.org/10.21227/yyer-m215. Accessed: Dec. 09, 2024.
@data{yyer-m215-24,
doi = {10.21227/yyer-m215},
url = {http://dx.doi.org/10.21227/yyer-m215},
author = {yesen chen },
publisher = {IEEE Dataport},
title = {EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning },
year = {2024} }
TY - DATA
T1 - EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning
AU - yesen chen
PY - 2024
PB - IEEE Dataport
UR - 10.21227/yyer-m215
ER -
yesen chen. (2024). EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning . IEEE Dataport. http://dx.doi.org/10.21227/yyer-m215
yesen chen, 2024. EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning . Available at: http://dx.doi.org/10.21227/yyer-m215.
yesen chen. (2024). "EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning ." Web.
1. yesen chen. EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning [Internet]. IEEE Dataport; 2024. Available from : http://dx.doi.org/10.21227/yyer-m215
yesen chen. "EMDSAC-ft: Bridging the Gap in Offline-to-Online Reinforcement Learning through Value Distribution Learning ." doi: 10.21227/yyer-m215