No abstract

Reinforcement learning, while being a highly popular learning technique for agents and multi-agent systems, has so far encountered difficulties when applying it to more complex domains due to scaling-up problems. This paper focuses on the use of domain knowledge to improve the convergence speed and optimality of various RL techniques. Specifically, we propose the use of high-level STRIPS operator knowledge in reward shaping to focus the search for the optimal policy. Empirical results show that the plan-based reward shaping approach outperforms other RL techniques, including alternative manual and MDP-based reward shaping when it is used in its basic form. We show that MDP-based reward shaping may fail and successful experiments with STRIPS-based shaping suggest modifications which can overcome encountered problems. The STRIPS-based method we propose allows expressing the same domain knowledge in a different way and the domain expert can choose whether to define an MDP or STRIPS planning task. We also evaluate the robustness of the proposed STRIPS-based technique to errors in the plan knowledge.

No abstract

The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that: • a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.

In recent years, multi-agent systems (MASs) have received increasing attention in the artificial intelligence community. Research in multi-agent systems involves the investigation of autonomous, rational and flexible behaviour of entities such as software programs or robots, and their interaction and coordination in such diverse areas as robotics (Kitano et al., 1997), information retrieval and management (Klusch, 1999), and simulation (Gilbert & Conte, 1995). When designing agent systems, it is impossible to foresee all the potential situations an agent may encounter and specify an agent behaviour optimally in advance. Agents therefore have to learn from, and adapt to, their environment, especially in a multi-agent setting.

This paper investigates the impact of reward shaping in multi-agent reinforcement learning as a way to incorporate domain knowledge about good strategies. In theory, potentialbased reward shaping does not alter the Nash Equilibria of a stochastic game, only the exploration of the shaped agent. We demonstrate empirically the performance of reward shaping in two problem domains within the context of RoboCup KeepAway by designing three reward shaping schemes, encouraging specific behaviour such as keeping a minimum distance from other players on the same team and taking on specific roles. The results illustrate that reward shaping with multiple, simultaneous learning agents can reduce the time needed to learn a suitable policy and can alter the final group performance.

a b s t r a c tPotential-based reward shaping has been shown to be a powerful method to improve the convergence rate of reinforcement learning agents. It is a flexible technique to incorporate background knowledge into temporal-difference learning in a principled way. However, the question remains of how to compute the potential function which is used to shape the reward that is given to the learning agent. In this paper, we show how, in the absence of knowledge to define the potential function manually, this function can be learned online in parallel with the actual reinforcement learning process. Two cases are considered. The first solution which is based on the multi-grid discretisation is designed for model-free reinforcement learning. In the second case, the approach for the prototypical model-based R-max algorithm is proposed. It learns the potential function using the free space assumption about the transitions in the environment. Two novel algorithms are presented and evaluated.

No abstract