Abstract | ||
---|---|---|
Our goal is to provide learning mechanisms to game agents so they are capable of adapting to new behaviors based on the actions of other agents. We introduce a new on-line reinforcement learning (RL) algorithm, ALeRT-AM, that includes an agent-modeling mechanism. We implemented this algorithm in BioWare Corp.'s role-playing game, Neverwinter Nights to evaluate its effectiveness in a real game. Our experiments compare agents who use ALeRT- AM with agents that use the non-agent modeling ALeRT RL algorithm and two other non-RL algorithms. We show that an ALeRT-AM agent is able to rapidly learn a winning strategy against other agents in a combat scenario and to adapt to changes in the environment. |
Year | Venue | Keywords |
---|---|---|
2009 | AIIDE | reinforcement learning |
Field | DocType | Citations |
Computer science,Artificial intelligence,Error-driven learning,Machine learning,Reinforcement learning | Conference | 3 |
PageRank | References | Authors |
0.41 | 8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Richard Zhao | 1 | 15 | 4.15 |
D. Szafron | 2 | 1579 | 210.88 |