We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning. The key idea is to learn a meta-critic: an action-value function neural network that learns to criticise any actor trying to solve any specified task. For sup...

Combining elements of the theory of dynamic programming with features appropriate for on-line learning has led to an approach Watkins has called incre-mental dynamic programming. Here we adopt this incremental dynamic programming point of view and obtain some preliminary mathematical results relevant to understanding the capabilities and limitations of actor-critic learning systems. Examples of...

We develop new rules for combining estimates obtained from each classi er in an ensemble. A variety of combination techniques have been previously suggested, including averaging probability estimates, as well as hard voting schemes. We introduce a critic associated with each classi er, whose objective is to predict the classi er's errors. Since the critic only tackles a two-class problem, its p...

Traditionally in many multiagent reinforcement learning researches, qualifying each individual agent’s behavior is responsibility of environment’s critic. However, in most practical cases, critic is not completely aware of effects of all agents’ actions on the team performance. Using agents’ learning history, it is possible to judge the correctness of their actions. To do so, we use team common...

Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings. Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it cannot scale well with growing amount of agents. In order ...

Example-based explanations are widely used in the effort to improve the interpretability of highly complex distributions. However, prototypes alone are rarely sufficient to represent the gist of the complexity. In order for users to construct better mental models and understand complex data distributions, we also need criticism to explain what are not captured by prototypes. Motivated by the Ba...

We demonstrate the use of qualitative models in the DHP method of training neurocontrollers. Two Fuzzy approaches to developing qualitative models are explored: a priori application of problem specific knowledge, and estimation of a first order TSK Fuzzy model. These approaches are demonstrated respectively on the cart-pole system and a non-linear multiple-inputmultiple-output plant proposed by...