On Generating Explanations for Reinforcement Learning Policies: An Empirical Study.
Mikihisa YuasaHuy T. TranRamavarapu S. SreenivasPublished in: CoRR (2023)
Keyphrases
- generating explanations
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- control policies
- reward function
- state space
- function approximation
- hierarchical reinforcement learning
- markov decision processes
- reinforcement learning agents
- dynamic programming
- control policy
- partially observable markov decision processes
- fitted q iteration
- cooperative multi agent systems
- model free
- machine learning
- policy gradient methods
- total reward
- reinforcement learning algorithms
- markov decision problems
- approximate policy iteration
- macro actions
- learning algorithm
- continuous state
- decision problems
- infinite horizon
- action space
- long run
- data sets
- action selection
- multiagent reinforcement learning
- reinforcement learning methods
- supervised learning
- least squares
- real robot
- robotic control
- actor critic
- multi agent
- finite state
- temporal difference learning