Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning

Oh, In-Seok; Rho, Seungeun; Moon, Sangbin; Lee, Hyoil; Chung, Ji-nyun

doi:10.48550/arxiv.1904.03821

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of (Oh et al 2019) encountered a related issue concerning no-op actions, when no other action can be executed. Although they tackle a quite different problem, namely a real-time fighting game, similarly as in our case they resolve it by skipping passive no-op actions.…”

Section: Related Workmentioning

confidence: 99%

“…This is because usually for the vast majority of match time no action is available to be played. Similarly as in (Oh et al 2019) we mitigate this issue by letting the agent perform no-op actions only when there is a non-trivial action available. The duration of no-op is a hyperparameter of our learning procedure and in the experiments we employ 4 seconds for card no-op and 4 seconds for spell no-op.…”

Section: No-op Actionsmentioning

confidence: 99%

See 1 more Smart Citation

Deep RL Agent for a Real-Time Action Strategy Game

Warchalski,

Radojevic,

Milosevic

2020

Preprint

View full text Add to dashboard Cite

We introduce a reinforcement learning environment based on Heroic -Magic Duel, a 1 v 1 action strategy game. This domain is non-trivial for several reasons: it is a real-time game, the state space is large, the information given to the player before and at each step of a match is imperfect, and distribution of actions is dynamic. Our main contribution is a deep reinforcement learning agent playing the game at a competitive level that we trained using PPO and self-play with multiple competing agents, employing only a simple reward of ±1 depending on the outcome of a single match. Our best self-play agent, obtains around 65% win rate against the existing AI and over 50% win rate against a top human player.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: No-op Actionsmentioning

confidence: 99%