The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large models for such applications. Prior work mainly emphasizes effective pretraining of large models for decision-making, with little exploration into how to perform data-efficient continual adaptation of these models for new tasks. Recognizing these constraints, we introduce TAIL (Task-specific Adapters for Imitation Learning), a framework for efficient adaptation to new control tasks. Inspired by recent advancements in parameter-efficient fine-tuning in language domains, we explore efficient fine-tuning techniques -- e.g., Bottleneck Adapters, P-Tuning, and Low-Rank Adaptation (LoRA) -- in TAIL to adapt large pretrained models for new tasks with limited demonstration data. Our extensive experiments in large-scale language-conditioned manipulation tasks comparing prevalent parameter-efficient fine-tuning techniques and adaptation baselines suggest that TAIL with LoRA can achieve the best post-adaptation performance with only 1\% of the trainable parameters of full fine-tuning, while avoiding catastrophic forgetting and preserving adaptation plasticity in continual learning settings.
The main challenge of offline reinforcement learning, where data is limited, arises from a sequence of counterfactual reasoning dilemmas within the realm of potential actions: What if we were to choose a different course of action? These circumstances frequently give rise to extrapolation errors, which tend to accumulate exponentially with the problem horizon. Hence, it becomes crucial to acknowledge that not all decision steps are equally important to the final outcome, and to budget the number of counterfactual decisions a policy make in order to control the extrapolation. Contrary to existing approaches that use regularization on either the policy or value function, we propose an approach to explicitly bound the amount of out-of-distribution actions during training. Specifically, our method utilizes dynamic programming to decide where to extrapolate and where not to, with an upper bound on the decisions different from behavior policy. It balances between the potential for improvement from taking out-of-distribution actions and the risk of making errors due to extrapolation. Theoretically, we justify our method by the constrained optimality of the fixed point solution to our $Q$ updating rules. Empirically, we show that the overall performance of our method is better than the state-of-the-art offline RL methods on tasks in the widely-used D4RL benchmarks.
We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of approximately solving a sequence of optimization problems where the objective function can change per iteration. The common approach to solving the problem is to employ modern variants of the stochastic gradient descent algorithm such as Adam. These optimizers maintain their own internal parameters such as estimates of the first and the second moment of the gradient, and update these parameters over time. Therefore, information obtained in previous iterations is being used to solve the optimization problem in the current iteration. We hypothesize that this can contaminate the internal parameters of the employed optimizer in situations where the optimization landscape of the previous iterations is quite different from the current iteration. To hedge against this effect, a simple idea is to reset the internal parameters of the optimizer when starting a new iteration. We empirically investigate this resetting strategy by employing various optimizers in conjunction with the Rainbow algorithm. We demonstrate that this simple modification unleashes the true potential of modern optimizers, and significantly improves the performance of deep RL on the Atari benchmark.
We study the convergence behavior of the celebrated temporal-difference (TD) learning algorithm. By looking at the algorithm through the lens of optimization, we first argue that TD can be viewed as an iterative optimization algorithm where the function to be minimized changes per iteration. By carefully investigating the divergence displayed by TD on a classical counter example, we identify two forces that determine the convergent or divergent behavior of the algorithm. We next formalize our discovery in the linear TD setting with quadratic loss and prove that convergence of TD hinges on the interplay between these two forces. We extend this optimization perspective to prove convergence of TD in a much broader setting than just linear approximation and squared loss. Our results provide a theoretical explanation for the successful application of TD in reinforcement learning.
Real-world deployment of machine learning models is challenging when data evolves over time. And data does evolve over time. While no model can work when data evolves in an arbitrary fashion, if there is some pattern to these changes, we might be able to design methods to address it. This paper addresses situations when data evolves gradually. We introduce a novel time-varying importance weight estimator that can detect gradual shifts in the distribution of data. Such an importance weight estimator allows the training method to selectively sample past data -- not just similar data from the past like a standard importance weight estimator would but also data that evolved in a similar fashion in the past. Our time-varying importance weight is quite general. We demonstrate different ways of implementing it that exploit some known structure in the evolution of data. We demonstrate and evaluate this approach on a variety of problems ranging from supervised learning tasks (multiple image classification datasets) where the data undergoes a sequence of gradual shifts of our design to reinforcement learning tasks (robotic manipulation and continuous control) where data undergoes a shift organically as the policy or the task changes.
We study task-agnostic continual reinforcement learning (TACRL) in which standard RL challenges are compounded with partial observability stemming from task agnosticism, as well as additional difficulties of continual learning (CL), i.e., learning on a non-stationary sequence of tasks. Here we compare TACRL methods with their soft upper bounds prescribed by previous literature: multi-task learning (MTL) methods which do not have to deal with non-stationary data distributions, as well as task-aware methods, which are allowed to operate under full observability. We consider a previously unexplored and straightforward baseline for TACRL, replay-based recurrent RL (3RL), in which we augment an RL algorithm with recurrent mechanisms to address partial observability and experience replay mechanisms to address catastrophic forgetting in CL. Studying empirical performance in a sequence of RL tasks, we find surprising occurrences of 3RL matching and overcoming the MTL and task-aware soft upper bounds. We lay out hypotheses that could explain this inflection point of continual and task-agnostic learning research. Our hypotheses are empirically tested in continuous control tasks via a large-scale study of the popular multi-task and continual learning benchmark Meta-World. By analyzing different training statistics including gradient conflict, we find evidence that 3RL's outperformance stems from its ability to quickly infer how new tasks relate with the previous ones, enabling forward transfer.
We employ Proximal Iteration for value-function optimization in reinforcement learning. Proximal Iteration is a computationally efficient technique that enables us to bias the optimization procedure towards more desirable solutions. As a concrete application of Proximal Iteration in deep reinforcement learning, we endow the objective function of the Deep Q-Network (DQN) agent with a proximal term to ensure that the online-network component of DQN remains in the vicinity of the target network. The resultant agent, which we call DQN with Proximal Iteration, or DQNPro, exhibits significant improvements over the original DQN on the Atari benchmark. Our results accentuate the power of employing sound optimization techniques for deep reinforcement learning.
Conditional quantile estimation is a key statistical learning challenge motivated by the need to quantify uncertainty in predictions or to model a diverse population without being overly reductive. As such, many models have been developed for this problem. Adopting a meta viewpoint, we propose a general framework (inspired by neural network optimization) for aggregating any number of conditional quantile models in order to boost predictive accuracy. We consider weighted ensembling strategies of increasing flexibility where the weights may vary over individual models, quantile levels, and feature values. An appeal of our approach is its portability: we ensure that estimated quantiles at adjacent levels do not cross by applying simple transformations through which gradients can be backpropagated, and this allows us to leverage the modern deep learning toolkit for building quantile ensembles. Our experiments confirm that ensembling can lead to big gains in accuracy, even when the constituent models are themselves powerful and flexible.
Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. The limited data in batch RL produces inherent uncertainty in value estimates of states/actions that were insufficiently represented in the training data. This leads to particularly severe extrapolation when our candidate policies diverge from one that generated the data. We propose to mitigate this issue via two straightforward penalties: a policy-constraint to reduce this divergence and a value-constraint that discourages overly optimistic estimates. Over a comprehensive set of 32 continuous-action batch RL benchmarks, our approach compares favorably to state-of-the-art methods, regardless of how the offline data were collected.