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.

Linear $Q$-Learning Does Not Diverge: Convergence Rates to a Bounded Set

$Q$-learning is one of the most fundamental reinforcement learning algorithms. Previously, it is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence. This paper instead establishes the first $L^2$ convergence rate of linear $Q$-learning to a bounded set. Notably, we do not make any modification to the original linear $Q$-learning algorithm, do not make any Bellman completeness assumption, and do not make any near-optimality assumption on the behavior policy. All we need is an $\epsilon$-softmax behavior policy with an adaptive temperature. The key to our analysis is the general result of stochastic approximations under Markovian noise with fast-changing transition functions. As a side product, we also use this general result to establish the $L^2$ convergence rate of tabular $Q$-learning with an $\epsilon$-softmax behavior policy, for which we rely on a novel pseudo-contraction property of the weighted Bellman optimality operator.

CRASH: Challenging Reinforcement-Learning Based Adversarial Scenarios For Safety Hardening

Ensuring the safety of autonomous vehicles (AVs) requires identifying rare but critical failure cases that on-road testing alone cannot discover. High-fidelity simulations provide a scalable alternative, but automatically generating realistic and diverse traffic scenarios that can effectively stress test AV motion planners remains a key challenge. This paper introduces CRASH - Challenging Reinforcement-learning based Adversarial scenarios for Safety Hardening - an adversarial deep reinforcement learning framework to address this issue. First CRASH can control adversarial Non Player Character (NPC) agents in an AV simulator to automatically induce collisions with the Ego vehicle, falsifying its motion planner. We also propose a novel approach, that we term safety hardening, which iteratively refines the motion planner by simulating improvement scenarios against adversarial agents, leveraging the failure cases to strengthen the AV stack. CRASH is evaluated on a simplified two-lane highway scenario, demonstrating its ability to falsify both rule-based and learning-based planners with collision rates exceeding 90%. Additionally, safety hardening reduces the Ego vehicle's collision rate by 26%. While preliminary, these results highlight RL-based safety hardening as a promising approach for scenario-driven simulation testing for autonomous vehicles.

Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise

This paper establishes the first almost sure convergence rate and the first maximal concentration bound with exponential tails for general contractive stochastic approximation algorithms with Markovian noise. As a corollary, we also obtain convergence rates in $L^p$. Key to our successes is a novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing (instead of constant) length. As applications, we provide the first almost sure convergence rate for $Q$-learning with Markovian samples without count-based learning rates. We also provide the first concentration bound for off-policy temporal difference learning with Markovian samples.

Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or designing proper behavior policies to collect data. However, these approaches ignore the safety of such behavior policies -- the designed behavior policies have no safety guarantee and may lead to severe damage during online executions. In this paper, to address the challenge of reducing variance while ensuring safety simultaneously, we propose an optimal variance-minimizing behavior policy under safety constraints. Theoretically, while ensuring safety constraints, our evaluation method is unbiased and has lower variance than on-policy evaluation. Empirically, our method is the only existing method to achieve both substantial variance reduction and safety constraint satisfaction. Furthermore, we show our method is even superior to previous methods in both variance reduction and execution safety.

Doubly Optimal Policy Evaluation for Reinforcement Learning

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting policy or data-processing method substantially deteriorates the variance of evaluation results over long time steps. Thus, policy evaluation often suffers from large variance and requires massive data to achieve the desired accuracy. In this work, we design an optimal combination of data-collecting policy and data-processing baseline. Theoretically, we prove our doubly optimal policy evaluation method is unbiased and guaranteed to have lower variance than previously best-performing methods. Empirically, compared with previous works, we show our method reduces variance substantially and achieves superior empirical performance.

Almost Sure Convergence of Average Reward Temporal Difference Learning

Tabular average reward Temporal Difference (TD) learning is perhaps the simplest and the most fundamental policy evaluation algorithm in average reward reinforcement learning. After at least 25 years since its discovery, we are finally able to provide a long-awaited almost sure convergence analysis. Namely, we are the first to prove that, under very mild conditions, tabular average reward TD converges almost surely to a sample path dependent fixed point. Key to this success is a new general stochastic approximation result concerning nonexpansive mappings with Markovian and additive noise, built on recent advances in stochastic Krasnoselskii-Mann iterations.

Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features

Temporal difference (TD) learning with linear function approximation, abbreviated as linear TD, is a classic and powerful prediction algorithm in reinforcement learning. While it is well understood that linear TD converges almost surely to a unique point, this convergence traditionally requires the assumption that the features used by the approximator are linearly independent. However, this linear independence assumption does not hold in many practical scenarios. This work is the first to establish the almost sure convergence of linear TD without requiring linearly independent features. In fact, we do not make any assumptions on the features. We prove that the approximated value function converges to a unique point and the weight iterates converge to a set. We also establish a notion of local stability of the weight iterates. Importantly, we do not need to introduce any other additional assumptions and do not need to make any modification to the linear TD algorithm. Key to our analysis is a novel characterization of bounded invariant sets of the mean ODE of linear TD.

Efficient Multi-Policy Evaluation for Reinforcement Learning

To unbiasedly evaluate multiple target policies, the dominant approach among RL practitioners is to run and evaluate each target policy separately. However, this evaluation method is far from efficient because samples are not shared across policies, and running target policies to evaluate themselves is actually not optimal. In this paper, we address these two weaknesses by designing a tailored behavior policy to reduce the variance of estimators across all target policies. Theoretically, we prove that executing this behavior policy with manyfold fewer samples outperforms on-policy evaluation on every target policy under characterized conditions. Empirically, we show our estimator has a substantially lower variance compared with previous best methods and achieves state-of-the-art performance in a broad range of environments.

Transformers Learn Temporal Difference Methods for In-Context Reinforcement Learning

In-context learning refers to the learning ability of a model during inference time without adapting its parameters. The input (i.e., prompt) to the model (e.g., transformers) consists of both a context (i.e., instance-label pairs) and a query instance. The model is then able to output a label for the query instance according to the context during inference. A possible explanation for in-context learning is that the forward pass of (linear) transformers implements iterations of gradient descent on the instance-label pairs in the context. In this paper, we prove by construction that transformers can also implement temporal difference (TD) learning in the forward pass, a phenomenon we refer to as in-context TD. We demonstrate the emergence of in-context TD after training the transformer with a multi-task TD algorithm, accompanied by theoretical analysis. Furthermore, we prove that transformers are expressive enough to implement many other policy evaluation algorithms in the forward pass, including residual gradient, TD with eligibility trace, and average-reward TD.