Aggregation of multiple Reinforcement Learning (RL) algorithms is a new and effective technique to improve the quality of Sequential Decision Making (SDM). The quality of a SDM depends on long-term rewards rather than the instant rewards. RL methods are often adopted to deal with SDM problems.
Although many RL algorithms have been developed, none is consistently better than the others. In addition, the parameters of RL algorithms significantly influence learning performances. There is no universal rule to guide the choice of algorithms and the setting of parameters. To handle this difficulty, a new multiple RL system - Aggregated Multiple Reinforcement Learning System (AMRLS) is developed. In AMRLS, each RL algorithm (learner) learns individually in a learning module and provides its output to an intelligent aggregation module. The aggregation module dynamically aggregates these outputs and provides a final decision. Then, all learners take the action and update their policies individually. The two processes are performed alternatively. AMRLS can deal with dynamic learning problems without the need to search for the optimal learning algorithm or the optimal values of learning parameters. It is claimed that several complementary learning algorithms can be integrated in AMRLS to improve the learning performance in terms of success rate, robustness, confidence, redundance, and complementariness.
There are two strategies for learning an optimal policy with RL methods. One is based on Value Function Learning (VFL), which learns an optimal policy expressed as a value function. The Temporal Difference RL (TDRL) methods are examples of this strategy. The other is based on Direct Policy Search (DPS), which directly searches for the optimal policy in the potential policy space. The Genetic Algorithms (GAs)-based RL (GARL) are instances of this strategy. A hybrid learning architecture of GARL and TDRL, HGATDRL, is proposed to combine them together to improve the learning ability.
AMRLS and HGATDRL are tested on several SDM problems, including the maze world problem, pursuit domain problem, cart-pole balancing system, mountain car problem, and flight control system. Experimental results show that the proposed framework and method can enhance the learning ability and improve learning performance of a multiple RL system.
| Identifer | oai:union.ndltd.org:WATERLOO/oai:uwspace.uwaterloo.ca:10012/2752 |
| Date | January 2007 |
| Creators | Jiang, Ju |
| Source Sets | University of Waterloo Electronic Theses Repository |
| Language | English |
| Detected Language | English |
| Type | Thesis or Dissertation |
| Format | 1403135 bytes, application/pdf |
Page generated in 0.0022 seconds