Aligning the world model with the environment for the agent's specific task is crucial in model-based reinforcement learning. While value-equivalent models may achieve better task awareness than maximum-likelihood models, they sacrifice a large amount of semantic information and face implementation issues. To combine the benefits of both types of models, we propose Task-aware Environment Modeling Pipeline with bi-level Optimization (TEMPO), a bi-level model learning framework that introduces an additional level of optimization on top of a maximum-likelihood model by incorporating a meta weighter network that weights each training sample. The meta weighter in the upper level learns to generate novel sample weights by minimizing a proposed task-aware model loss. The model in the lower level focuses on important samples while maintaining rich semantic information in state representations. We evaluate TEMPO on a variety of continuous and discrete control tasks from the DeepMind Control Suite and Atari video games. Our results demonstrate that TEMPO achieves state-of-the-art performance regarding asymptotic performance, training stability, and convergence speed.

We will emphasize it in the discussion part.

Surprisingly, however, the optimal rate in terms of Bellman error for the VI setup was not known, and finding a general acceleration mechanism has been an open problem. In this paper, we present the first accelerated VI for both the Bellman consistency and optimality operators. Our method, called Anc-VI, is based on an anchoring mechanism (distinct from Nesterov's acceleration), and it reduces the Bellman error faster than standard VI. In particular, Anc-VI exhibits a O(1/k)-rate for γ 1 or even γ = 1, while standard VI has rate O(1) for γ 1 1/k, where k is the iteration count. We also provide a complexity lower bound matching the upper bound up to a constant factor of 4, thereby establishing optimality of the accelerated rate of Anc-VI. Finally, we show that the anchoring mechanism provides the same benefit in the approximate VI and Gauss-Seidel VI setups as well.

Self-imitation learning motivated by lower-bound Q-learning is a novel and effective approach for off-policy learning. In this work, we propose a n-step lower bound which generalizes the original return-based lower-bound Q-learning, and introduce a new family of self-imitation learning algorithms. To provide a formal motivation for the potential performance gains provided by self-imitation learning, we show that n-step lower bound Q-learning achieves a trade-off between fixed point bias and contraction rate, drawing close connections to the popular uncorrected n-step Q-learning. We finally show that n-step lower bound Q-learning is a more robust alternative to return-based self-imitation learning and uncorrected n-step, over a wide range of continuous control benchmark tasks.

In reinforcement learning with image-based inputs, it is crucial to establish a robust and generalizable state representation. Recent advancements in metric learning, such as deep bisimulation metric approaches, have shown promising results in learning structured low-dimensional representation space from pixel observations, where the distance between states is measured based on task-relevant features. However, these approaches face challenges in demanding generalization tasks and scenarios with non-informative rewards. This is because they fail to capture sufficient long-term information in the learned representations. To address these challenges, we propose a novel State Chrono Representation (SCR) approach. SCR augments state metric-based representations by incorporating extensive temporal information into the update step of bisimulation metric learning. It learns state distances within a temporal framework that considers both future dynamics and cumulative rewards over current and long-term future states. Our learning strategy effectively incorporates future behavioral information into the representation space without introducing a significant number of additional parameters for modeling dynamics. Extensive experiments conducted in DeepMind Control and Meta-World environments demonstrate that SCR achieves better performance comparing to other recent metric-based methods in demanding generalization tasks.

Most compilers for machine learning (ML) frameworks need to solve many correlated optimization problems to generate efficient machine code. Current ML compilers rely on heuristics based algorithms to solve these optimization problems one at a time. However, this approach is not only hard to maintain but often leads to sub-optimal solutions especially for newer model architectures. Existing learning based approaches in the literature are sample inefficient, tackle a single optimization problem, and do not generalize to unseen graphs making them infeasible to be deployed in practice. To address these limitations, we propose an end-to-end, transferable deep reinforcement learning method for computational graph optimization (GO), based on a scalable sequential attention mechanism over an inductive graph neural network. GO generates decisions on the entire graph rather than on each individual node autoregressively, drastically speeding up the search compared to prior methods. Moreover, we propose recurrent attention layers to jointly optimize dependent graph optimization tasks and demonstrate 33%-60% speedup on three graph optimization tasks compared to TensorFlow default optimization. On a diverse set of representative graphs consisting of up to 80,000 nodes, including Inception-v3, Transformer-XL, and WaveNet, GO achieves on average 21% improvement over human experts and 18% improvement over the prior state of the art with 15 faster convergence, on a device placement task evaluated in real systems.

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with selfimprovement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to process long-term dependencies, which provides an opportunity for in-context RL to solve tasks that require long-term memory. To this end, we first implement Decision Mamba (DM) by replacing the backbone of Decision Transformer (DT).

We thank all reviewers for their careful reading of the paper, thoughtful feedback, and constructive suggestions. Each reviewer's major comments are addressed below. Reviewer 1. Thanks for your time and effort devoted to reviewing our submission, as well as for the positive comments Distinct novelties relative to Ref. [31] are: i) Algorithm: The present submission develops Following your suggestion, [31] will be discussed more thoroughly in the revised paper. We will respectfully disagree that it "makes more sense to take a decaying step-size." Due to space limitation, the focus of this paper was placed on analysis under both IID and Markovian data.

Recent theoretical and experimental results suggest that the dopamine system implements distributional temporal difference backups, allowing learning of the entire distributions of the long-run values of states rather than just their expected values. However, the distributional codes explored so far rely on a complex imputation step which crucially relies on spatial non-locality: in order to compute reward prediction errors, units must know not only their own state but also the states of the other units. It is far from clear how these steps could be implemented in realistic neural circuits. Here, we introduce the Laplace code: a local temporal difference code for distributional reinforcement learning that is representationally powerful and computationally straightforward. The code decomposes value distributions and prediction errors across three separated dimensions: reward magnitude (related to distributional quantiles), temporal discounting (related to the Laplace transform of future rewards) and time horizon (related to eligibility traces). Besides lending itself to a local learning rule, the decomposition recovers the temporal evolution of the immediate reward distribution, indicating all possible rewards at all future times. This increases representational capacity and allows for temporally-flexible computations that immediately adjust to changing horizons or discount factors.

We will also expand Section 2 to make it more gradual, stating theorems and definitions explicitly.