FGYM: Toolkit for Benchmarking FPGA based Reinforcement Learning Algorithms.
Nathaniel PeuraYuan MengSanmukh R. KuppannagariViktor K. PrasannaPublished in: FPL (2021)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- eligibility traces
- reinforcement learning problems
- reinforcement learning methods
- learning algorithm
- temporal difference
- function approximation
- policy search
- reward function
- stochastic games
- partially observable environments
- reward shaping
- markov chain
- random variables
- cost function
- search space