A benchmark study reporting that Expected SARSA and deep Q-learning agents score highest among tested tabular and deep RL algorithms on a Hanabi environment.
A theoretical and empirical analysis of expected sarsa
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforcement Learning for Hanabi
A benchmark study reporting that Expected SARSA and deep Q-learning agents score highest among tested tabular and deep RL algorithms on a Hanabi environment.