Advanced biological intelligence learns efficiently from an information-rich stream of stimulus information, even when feedback on behaviour quality is sparse or absent. Such learning exploits implicit assumptions about task domains. We refer to such learning as Domain-Adapted Learning (DAL). In contrast, AI learning algorithms rely on explicit externally provided measures of behaviour quality to acquire fit behaviour. This imposes an information bottleneck that precludes learning from diverse non-reward stimulus information, limiting learning efficiency. We consider the question of how biological evolution circumvents this bottleneck to produce DAL. We propose that species first evolve the ability to learn from reward signals, providing inefficient (bottlenecked) but broad adaptivity. From there, integration of non-reward information into the learning process can proceed via gradual accumulation of biases induced by such information on specific task domains. This scenario provides a biologically plausible pathway towards bottleneck-free, domain-adapted learning. Focusing on the second phase of this scenario, we set up a population of NNs with reward-driven learning modelled as Reinforcement Learning (A2C), and allow evolution to improve learning efficiency by integrating non-reward information into the learning process using a neuromodulatory update mechanism. On a navigation task in continuous 2D space, evolved DAL agents show a 300-fold increase in learning speed compared to pure RL agents. Evolution is found to eliminate reliance on reward information altogether, allowing DAL agents to learn from non-reward information exclusively, using local neuromodulation-based connection weight updates only.

We consider the problem of open-goal planning for robotic cloth manipulation. Core of our system is a neural network trained as a forward model of cloth behaviour under manipulation, with planning performed through backpropagation. We introduce a neural network-based routine for estimating mesh representations from voxel input, and perform planning in mesh format internally. We address the problem of planning with incomplete domain knowledge by means of an explicit epistemic uncertainty signal. This signal is calculated from prediction divergence between two instances of the forward model network and used to avoid epistemic uncertainty during planning. Finally, we introduce logic for handling restriction of grasp points to a discrete set of candidates, in order to accommodate graspability constraints imposed by robotic hardware. We evaluate the system's mesh estimation, prediction, and planning ability on simulated cloth for sequences of one to three manipulations. Comparative experiments confirm that planning on basis of estimated meshes improves accuracy compared to voxel-based planning, and that epistemic uncertainty avoidance improves performance under conditions of incomplete domain knowledge. We additionally present qualitative results on robot hardware.