EDGE: Explaining Deep Reinforcement Learning Policies.
Wenbo GuoXian WuUsmann KhanXinyu XingPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- markov decision processes
- control policies
- state space
- function approximation
- partially observable markov decision processes
- reward function
- hierarchical reinforcement learning
- reinforcement learning agents
- reinforcement learning algorithms
- fitted q iteration
- cooperative multi agent systems
- model free
- total reward
- edge information
- weighted graph
- multi agent
- policy gradient methods
- markov decision problems
- machine learning
- approximate policy iteration
- learning process
- dynamic programming
- edge detection
- state abstraction
- multi agent reinforcement learning
- infinite horizon
- decision problems
- finite state
- continuous state
- management policies
- average reward
- control policy
- deep learning
- real robot
- multiple scales
- learning classifier systems
- long run