A Survey of In-Context Reinforcement Learning

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning on additional context such as their action-observation histories. This paper surveys work on such behavior, known as in-context reinforcement learning.

Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps

In reinforcement learning (RL), it is common to apply techniques used broadly in machine learning such as neural network function approximators and momentum-based optimizers. However, such tools were largely developed for supervised learning rather than nonstationary RL, leading practitioners to adopt target networks, clipped policy updates, and other RL-specific implementation tricks to combat this mismatch, rather than directly adapting this toolchain for use in RL. In this paper, we take a different approach and instead address the effect of nonstationarity by adapting the widely used Adam optimiser. We first analyse the impact of nonstationary gradient magnitude -- such as that caused by a change in target network -- on Adam's update size, demonstrating that such a change can lead to large updates and hence sub-optimal performance. To address this, we introduce Adam-Rel. Rather than using the global timestep in the Adam update, Adam-Rel uses the local timestep within an epoch, essentially resetting Adam's timestep to 0 after target changes. We demonstrate that this avoids large updates and reduces to learning rate annealing in the absence of such increases in gradient magnitude. Evaluating Adam-Rel in both on-policy and off-policy RL, we demonstrate improved performance in both Atari and Craftax. We then show that increases in gradient norm occur in RL in practice, and examine the differences between our theoretical model and the observed data.

Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling

Ensuring the safety of autonomous vehicles (AVs) requires both accurate estimation of their performance and efficient discovery of potential failure cases. This paper introduces Bayesian adaptive multifidelity sampling (BAMS), which leverages the power of adaptive Bayesian sampling to achieve efficient discovery while simultaneously estimating the rate of adverse events. BAMS prioritizes exploration of regions with potentially low performance, leading to the identification of novel and critical scenarios that traditional methods might miss. Using real-world AV data we demonstrate that BAMS discovers 10 times as many issues as Monte Carlo (MC) and importance sampling (IS) baselines, while at the same time generating rate estimates with variances 15 and 6 times narrower than MC and IS baselines respectively.

IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving

Developing autonomous vehicles that can navigate complex environments with human-level safety and efficiency is a central goal in self-driving research. A common approach to achieving this is imitation learning, where agents are trained to mimic human expert demonstrations collected from real-world driving scenarios. However, discrepancies between human perception and the self-driving car's sensors can introduce an \textit{imitation gap}, leading to imitation learning failures. In this work, we introduce \textbf{IGDrivSim}, a benchmark built on top of the Waymax simulator, designed to investigate the effects of the imitation gap in learning autonomous driving policy from human expert demonstrations. Our experiments show that this perception gap between human experts and self-driving agents can hinder the learning of safe and effective driving behaviors. We further show that combining imitation with reinforcement learning, using a simple penalty reward for prohibited behaviors, effectively mitigates these failures. Our code is open-sourced at: https://github.com/clemgris/IGDrivSim.git.

Can Learned Optimization Make Reinforcement Learning Less Difficult?

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from high degrees of plasticity loss; and requires exploration to prevent premature convergence to local optima and maximize return. In this paper, we consider whether learned optimization can help overcome these problems. Our method, Learned Optimization for Plasticity, Exploration and Non-stationarity (OPEN), meta-learns an update rule whose input features and output structure are informed by previously proposed solutions to these difficulties. We show that our parameterization is flexible enough to enable meta-learning in diverse learning contexts, including the ability to use stochasticity for exploration. Our experiments demonstrate that when meta-trained on single and small sets of environments, OPEN outperforms or equals traditionally used optimizers. Furthermore, OPEN shows strong generalization across a distribution of environments and a range of agent architectures.

A Bayesian Solution To The Imitation Gap

In many real-world settings, an agent must learn to act in environments where no reward signal can be specified, but a set of expert demonstrations is available. Imitation learning (IL) is a popular framework for learning policies from such demonstrations. However, in some cases, differences in observability between the expert and the agent can give rise to an imitation gap such that the expert's policy is not optimal for the agent and a naive application of IL can fail catastrophically. In particular, if the expert observes the Markov state and the agent does not, then the expert will not demonstrate the information-gathering behavior needed by the agent but not the expert. In this paper, we propose a Bayesian solution to the Imitation Gap (BIG), first using the expert demonstrations, together with a prior specifying the cost of exploratory behavior that is not demonstrated, to infer a posterior over rewards with Bayesian inverse reinforcement learning (IRL). BIG then uses the reward posterior to learn a Bayes-optimal policy. Our experiments show that BIG, unlike IL, allows the agent to explore at test time when presented with an imitation gap, whilst still learning to behave optimally using expert demonstrations when no such gap exists.

UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarios

This paper introduces UniGen, a novel approach to generating new traffic scenarios for evaluating and improving autonomous driving software through simulation. Our approach models all driving scenario elements in a unified model: the position of new agents, their initial state, and their future motion trajectories. By predicting the distributions of all these variables from a shared global scenario embedding, we ensure that the final generated scenario is fully conditioned on all available context in the existing scene. Our unified modeling approach, combined with autoregressive agent injection, conditions the placement and motion trajectory of every new agent on all existing agents and their trajectories, leading to realistic scenarios with low collision rates. Our experimental results show that UniGen outperforms prior state of the art on the Waymo Open Motion Dataset.

Policy-Guided Diffusion

In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring policy conservatism to avoid instability and overestimation bias. Autoregressive world models offer a different solution to this by generating synthetic, on-policy experience. However, in practice, model rollouts must be severely truncated to avoid compounding error. As an alternative, we propose policy-guided diffusion. Our method uses diffusion models to generate entire trajectories under the behavior distribution, applying guidance from the target policy to move synthetic experience further on-policy. We show that policy-guided diffusion models a regularized form of the target distribution that balances action likelihood under both the target and behavior policies, leading to plausible trajectories with high target policy probability, while retaining a lower dynamics error than an offline world model baseline. Using synthetic experience from policy-guided diffusion as a drop-in substitute for real data, we demonstrate significant improvements in performance across a range of standard offline reinforcement learning algorithms and environments. Our approach provides an effective alternative to autoregressive offline world models, opening the door to the controllable generation of synthetic training data.

SplAgger: Split Aggregation for Meta-Reinforcement Learning

A core ambition of reinforcement learning (RL) is the creation of agents capable of rapid learning in novel tasks. Meta-RL aims to achieve this by directly learning such agents. Black box methods do so by training off-the-shelf sequence models end-to-end. By contrast, task inference methods explicitly infer a posterior distribution over the unknown task, typically using distinct objectives and sequence models designed to enable task inference. Recent work has shown that task inference methods are not necessary for strong performance. However, it remains unclear whether task inference sequence models are beneficial even when task inference objectives are not. In this paper, we present strong evidence that task inference sequence models are still beneficial. In particular, we investigate sequence models with permutation invariant aggregation, which exploit the fact that, due to the Markov property, the task posterior does not depend on the order of data. We empirically confirm the advantage of permutation invariant sequence models without the use of task inference objectives. However, we also find, surprisingly, that there are multiple conditions under which permutation variance remains useful. Therefore, we propose SplAgger, which uses both permutation variant and invariant components to achieve the best of both worlds, outperforming all baselines on continuous control and memory environments.

Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control

Learning a universal policy across different robot morphologies can significantly improve learning efficiency and enable zero-shot generalization to unseen morphologies. However, learning a highly performant universal policy requires sophisticated architectures like transformers (TF) that have larger memory and computational cost than simpler multi-layer perceptrons (MLP). To achieve both good performance like TF and high efficiency like MLP at inference time, we propose HyperDistill, which consists of: (1) A morphology-conditioned hypernetwork (HN) that generates robot-wise MLP policies, and (2) A policy distillation approach that is essential for successful training. We show that on UNIMAL, a benchmark with hundreds of diverse morphologies, HyperDistill performs as well as a universal TF teacher policy on both training and unseen test robots, but reduces model size by 6-14 times, and computational cost by 67-160 times in different environments. Our analysis attributes the efficiency advantage of HyperDistill at inference time to knowledge decoupling, i.e., the ability to decouple inter-task and intra-task knowledge, a general principle that could also be applied to improve inference efficiency in other domains.