The Option Keyboard (OK) was recently proposed as a method for transferring behavioral knowledge across tasks. OK transfers knowledge by adaptively combining subsets of known behaviors using Successor Features (SFs) and Generalized Policy Improvement (GPI). However, it relies on hand-designed state-features and task encodings which are cumbersome to design for every new environment. In this work, we propose the "Successor Features Keyboard" (SFK), which enables transfer with discovered state-features and task encodings. To enable discovery, we propose the "Categorical Successor Feature Approximator" (CSFA), a novel learning algorithm for estimating SFs while jointly discovering state-features and task encodings. With SFK and CSFA, we achieve the first demonstration of transfer with SFs in a challenging 3D environment where all the necessary representations are discovered. We first compare CSFA against other methods for approximating SFs and show that only CSFA discovers representations compatible with SF&GPI at this scale. We then compare SFK against transfer learning baselines and show that it transfers most quickly to long-horizon tasks.
What can be learned about causality and experimentation from passive data? This question is salient given recent successes of passively-trained language models in interactive domains such as tool use. Passive learning is inherently limited. However, we show that purely passive learning can in fact allow an agent to learn generalizable strategies for determining and using causal structures, as long as the agent can intervene at test time. We formally illustrate that learning a strategy of first experimenting, then seeking goals, can allow generalization from passive learning in principle. We then show empirically that agents trained via imitation on expert data can indeed generalize at test time to infer and use causal links which are never present in the training data; these agents can also generalize experimentation strategies to novel variable sets never observed in training. We then show that strategies for causal intervention and exploitation can be generalized from passive data even in a more complex environment with high-dimensional observations, with the support of natural language explanations. Explanations can even allow passive learners to generalize out-of-distribution from perfectly-confounded training data. Finally, we show that language models, trained only on passive next-word prediction, can generalize causal intervention strategies from a few-shot prompt containing examples of experimentation, together with explanations and reasoning. These results highlight the surprising power of passive learning of active causal strategies, and may help to understand the behaviors and capabilities of language models.
How should we compare the capabilities of language models and humans? Here, I consider a case study: processing of recursively nested grammatical structures. Prior work has suggested that language models cannot handle these structures as reliably as humans can. However, the humans were provided with instructions and training before being evaluated, while the language models were evaluated zero-shot. I therefore attempt to more closely match the evaluation paradigms by providing language models with few-shot prompts. A simple prompt, which contains substantially less content than the human training, allows large language models to consistently outperform the human results. The same prompt even allows extrapolation to more deeply nested conditions than have been tested in humans. Further, a reanalysis of the prior human experiments suggests that the humans may not perform above chance at the difficult structures initially. These results suggest that large language models can in fact process recursively nested grammatical structures comparably to humans. This case study highlights how discrepancies in the quantity of experiment-specific context can confound comparisons of language models and humans. I use this case study to reflect on the broader challenge of comparing human and model capabilities, and to suggest that there is an important difference between evaluating cognitive models of a specific phenomenon and evaluating broadly-trained models.
Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to recall the details of a single timestep that is followed by distractor tasks. To address these limitations, we propose a Hierarchical Transformer Memory (HTM), which helps agents to remember the past in detail. HTM stores memories by dividing the past into chunks, and recalls by first performing high-level attention over coarse summaries of the chunks, and then performing detailed attention within only the most relevant chunks. An agent with HTM can therefore "mentally time-travel" -- remember past events in detail without attending to all intervening events. We show that agents with HTM substantially outperform agents with other memory architectures at tasks requiring long-term recall, retention, or reasoning over memory. These include recalling where an object is hidden in a 3D environment, rapidly learning to navigate efficiently in a new neighborhood, and rapidly learning and retaining new object names. Agents with HTM can extrapolate to task sequences an order of magnitude longer than they were trained on, and can even generalize zero-shot from a meta-learning setting to maintaining knowledge across episodes. HTM improves agent sample efficiency, generalization, and generality (by solving tasks that previously required specialized architectures). Our work is a step towards agents that can learn, interact, and adapt in complex and temporally-extended environments.
GANs provide a framework for training generative models which mimic a data distribution. However, in many cases we wish to train these generative models to optimize some auxiliary objective function within the data it generates, such as making more aesthetically pleasing images. In some cases, these objective functions are difficult to evaluate, e.g. they may require human interaction. Here, we develop a system for efficiently improving a GAN to target an objective involving human interaction, specifically generating images that increase rates of positive user interactions. To improve the generative model, we build a model of human behavior in the targeted domain from a relatively small set of interactions, and then use this behavioral model as an auxiliary loss function to improve the generative model. We show that this system is successful at improving positive interaction rates, at least on simulated data, and characterize some of the factors that affect its performance.