A Minimal Approach for Natural Language Action Space in Text-based Games.
Dongwon RyuMeng FangGholamreza HaffariShirui PanEhsan ShareghiPublished in: CoNLL (2023)
Keyphrases
- action space
- natural language
- state space
- markov decision processes
- real valued
- reinforcement learning
- state and action spaces
- state action
- action selection
- continuous state spaces
- stochastic games
- stochastic processes
- nash equilibria
- cooperative
- information extraction
- evaluation function
- single agent
- markov decision process
- particle filtering
- average reward
- nash equilibrium
- game theory
- orders of magnitude
- markov chain
- optimal solution