A parallelized deep Q-network with separate frequency and spreading factor heads nearly doubles simulated throughput against a moving reactive jammer without epsilon-greedy exploration.
Deep reinforcement learning that matters,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Achieving Hiding and Smart Anti-Jamming Communication: A Parallel DRL Approach against Moving Reactive Jammer
A parallelized deep Q-network with separate frequency and spreading factor heads nearly doubles simulated throughput against a moving reactive jammer without epsilon-greedy exploration.