Competitive Deep Reinforcement Learning over a Pokémon Battling Simulator.
David SimõesSimão ReisNuno LauLuís Paulo ReisPublished in: ICARSC (2020)
Keyphrases
- reinforcement learning
- real robot
- function approximation
- reinforcement learning algorithms
- simulation model
- multi agent
- state space
- machine learning
- stochastic approximation
- action selection
- model free
- deep learning
- temporal difference learning
- evolutionary robotics
- multi agent reinforcement learning
- robotic control
- data sets
- markov decision process
- test bed
- markov decision processes
- optimal policy
- operating system
- decision making
- real world