Why? Why not? When? Visual Explanations of Agent Behaviour in Reinforcement Learning.
Aditi MishraUtkarsh SoniJinbin HuangChris BryanPublished in: PacificVis (2022)
Keyphrases
- reinforcement learning
- reward function
- multi agent
- action selection
- multi agent systems
- multiagent systems
- visual information
- learning agent
- multi agent environments
- markov decision processes
- autonomous agents
- intelligent agents
- reinforcement learning algorithms
- visual representations
- agent model
- state abstraction
- agent receives
- multiple agents
- learning capabilities
- reinforcement learning agents
- function approximation
- software agents
- temporal difference
- optimal policy
- dynamic environments
- autonomous learning
- learning agents
- state space
- exploration strategy
- generating explanations
- decision making
- markov decision process
- learning algorithm
- visual features
- partially observable
- visual perception
- agent systems
- multiagent reinforcement learning
- model free
- qualitative models
- visual representation
- single agent
- internal state
- multi agent reinforcement learning
- decision theoretic
- reward shaping
- behavioural patterns
- open multiagent systems