Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics.
Baihan LinGuillermo A. CecchiDjallel BouneffoufPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- artificial intelligence
- markov decision process
- markov decision processes
- state space
- machine learning
- partially observable
- reinforcement learning problems
- partially observable environments
- function approximation
- policy gradient
- policy iteration
- reinforcement learning algorithms
- function approximators
- action space
- dynamic model
- control policies
- approximate dynamic programming
- state and action spaces
- knowledge representation
- markov decision problems
- control policy
- expert systems
- dynamical systems
- actor critic
- dynamic programming
- recommender systems
- continuous state spaces
- temporal difference
- reward function
- intelligent systems
- partially observable markov decision processes
- john mccarthy
- continuous state
- decision process
- policy evaluation
- multi agent reinforcement learning
- control problems
- learning algorithm
- average reward
- ai systems
- neural network
- model free
- learning process
- rl algorithms
- partially observable domains
- multi agent
- case based reasoning
- transition model
- knowledge based systems
- decision problems
- infinite horizon
- computational intelligence
- inverse reinforcement learning
- agent learns
- long run
- state action
- reinforcement learning methods
- policy gradient methods