Link to original article

Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Caution when interpreting Deepmind's In-context RL paper, published by Sam Marks on November 1, 2022 on The AI Alignment Forum. Lots of people I know have had pretty strong reactions to the recent Deepmind paper, which claims to have gotten a transformer to learn an RL algorithm by training it on an RL agent's training trajectories. At first, I too was pretty shocked -- this paper seemed to provide strong evidence of a mesa-optimizer in the wild. But digging into the paper a bit more, I'm quite unimpressed and don't think that in-context RL is the correct way to interpret the experiments that the authors actually did. This post is a quick, low-effort attempt to write out my thoughts on this. Recall that in this paper, the authors pick some RL algorithm, use it to train RL agents on some tasks, and save the trajectories generated during training; then they train a transformer to autoregressively model said trajectories, and deploy the transformer on some novel tasks. So for concreteness, during training the transformer sees inputs that look like which were excerpted from an RL agent's training on some task (out of a set of training tasks) and which span multiple episodes (i.e. at some point in this input trajectory, one episode ended and the next episode began). The transformer is trained to guess the action an+c that comes next. In deployment, the inputs are determined by the transformer's own selections, with the environment providing the states and rewards. The authors call this algorithmic distillation (AD). Many people I know have skimmed the paper and come away with an understanding something like: In this paper, RL agents are trained on diverse tasks, e.g. playing many different Atari games, and the resulting transcripts are used as training data for AD. Then the AD agent is deployed on a new task, e.g. playing a held-out Atari game. The AD agent is able to learn to play this novel game, which can only be explained by the model implementing an reasonably general RL algorithm. This sounds a whole lot like a mesa-optimizer. This understanding is incorrect, with two key issues. First the training tasks used in this paper are all extremely similar to each other and to the deployment task; in fact, I think they only ought to count as different under a pathologically narrow notion of "task." And second, the tasks involved are extremely simple. The complaints taken together challenge the conclusion that the only way for the AD agent to do well on its deployment task is by implementing a general-purpose RL algorithm. In fact, as I'll explain in more detail below, I'd be quite surprised if it were. For concreteness, I'll focus here on one family of experiments, Dark Room, that appeared in the paper, but my complaint applies just as well to the other experiments in the paper. The paper describes the Dark Room environment as: a 2D discrete POMDP where an agent spawns in a room and must find a goal location. The agent only knows its own (x, y) coordinates but does not know the goal location and must infer it from the reward. The room size is 9 × 9, the possible actions are one step left, right, up, down, and no-op, the episode length is 20, and the agent resets at the center of the map. ... [T]he agent receives r = 1 every time the goal is reached. ... When not r = 1, then r = 0. To be clear, Dark Room is not a single task, but an environment supporting a family of tasks, where each task is corresponds to a particular choice of goal location (so there are 81 possible tasks in this environment, one for each location in the 9 x 9 room; note that this is an unusually narrow notion of which tasks count as different). The data on which the AD agent is trained look like: {many episodes of an agent learning to move towards goal position 1}, {many episodes of an agent learning to ...