Policy-based Reinforcement Learning for Generalisation in Interactive Text-based Environments.
Edan ToledoJan BuysJonathan ShockPublished in: EACL (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- partially observable environments
- state space
- partially observable
- function approximation
- interactive systems
- function approximators
- policy evaluation
- markov decision processes
- real world
- control policy
- policy gradient
- state action
- state and action spaces
- multimedia
- approximate dynamic programming
- actor critic
- reinforcement learning algorithms
- multi agent environments
- temporal difference
- dynamic environments
- dynamic programming
- continuous state
- control policies
- learning algorithm
- interactive narrative
- rl algorithms
- robot control
- action space
- model free
- user friendly
- user interaction
- machine learning
- average reward
- markov decision problems
- policy iteration
- infinite horizon
- learning problems
- transition model
- virtual reality
- computer graphics
- reinforcement learning problems
- mobile robot