R-MAX - A general polynomial time algorithm for near-optimal reinforcement learning

Keyphrases

• Near-optimal 100%
• Polynomial-time Algorithm 100%
• Reinforcement Learning 100%
• General Polynomial 100%
• Optimal Reinforcement 100%
• Repeated Games 66%
• Polynomial Time 33%
• Average Reward 33%
• Optimal Policy 33%
• Under Uncertainty 33%
• Stochastic Games 33%
• Single Controller 33%
• Singh 33%
• Megiddo 33%
• Zero-sum Stochastic Games 33%
• Reinforcement Learning Algorithm 33%
• Inaccurate Models 33%
• RL Algorithm 33%
• Uncertainty Bias 33%
• Model-based Reinforcement Learning 33%
• Optimal Learning 33%

Computer Science

• Polynomial Time Algorithm 100%
• Reinforcement Learning 100%
• Polynomial Time 50%
• Model-Based Reinforcement Learning 50%