Communication is crucial in multi-agent reinforcement learning when agents are not able to observe the full state of the environment. The most common approach to allow learned communication between agents is the use of a differentiable communication channel that allows gradients to flow between agents as a form of feedback. However, this is challenging when we want to use discrete messages to reduce the message size, since gradients cannot flow through a discrete communication channel. Previous work proposed methods to deal with this problem. However, these methods are tested in different communication learning architectures and environments, making it hard to compare them. In this paper, we compare several state-of-the-art discretization methods as well as a novel approach. We do this comparison in the context of communication learning using gradients from other agents and perform tests on several environments. In addition, we present COMA-DIAL, a communication learning approach based on DIAL and COMA extended with learning rate scaling and adapted exploration. Using COMA-DIAL allows us to perform experiments on more complex environments. Our results show that the novel ST-DRU method, proposed in this paper, achieves the best results out of all discretization methods across the different environments. It achieves the best or close to the best performance in each of the experiments and is the only method that does not fail on any of the tested environments.

Congestion Control (CC) plays a fundamental role in optimizing traffic in Data Center Networks (DCN). Currently, DCNs mainly implement two main CC protocols: DCTCP and DCQCN. Both protocols -- and their main variants -- are based on Explicit Congestion Notification (ECN), where intermediate switches mark packets when they detect congestion. The ECN configuration is thus a crucial aspect on the performance of CC protocols. Nowadays, network experts set static ECN parameters carefully selected to optimize the average network performance. However, today's high-speed DCNs experience quick and abrupt changes that severely change the network state (e.g., dynamic traffic workloads, incast events, failures). This leads to under-utilization and sub-optimal performance. This paper presents GraphCC, a novel Machine Learning-based framework for in-network CC optimization. Our distributed solution relies on a novel combination of Multi-agent Reinforcement Learning (MARL) and Graph Neural Networks (GNN), and it is compatible with widely deployed ECN-based CC protocols. GraphCC deploys distributed agents on switches that communicate with their neighbors to cooperate and optimize the global ECN configuration. In our evaluation, we test the performance of GraphCC under a wide variety of scenarios, focusing on the capability of this solution to adapt to new scenarios unseen during training (e.g., new traffic workloads, failures, upgrades). We compare GraphCC with a state-of-the-art MARL-based solution for ECN tuning -- ACC -- and observe that our proposed solution outperforms the state-of-the-art baseline in all of the evaluation scenarios, showing improvements up to $20\%$ in Flow Completion Time as well as significant reductions in buffer occupancy ($38.0-85.7\%$).

We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations. The reward is the novelty of the surprise rather than the surprise norm. We estimate the surprise novelty as retrieval errors of a memory network wherein the memory stores and reconstructs surprises. Our surprise memory (SM) augments the capability of surprise-based intrinsic motivators, maintaining the agent's interest in exciting exploration while reducing unwanted attraction to unpredictable or noisy observations. Our experiments demonstrate that the SM combined with various surprise predictors exhibits efficient exploring behaviors and significantly boosts the final performance in sparse reward environments, including Noisy-TV, navigation and challenging Atari games.

This paper presents an empirical exploration of non-transitivity in perfect-information games, specifically focusing on Xiangqi, a traditional Chinese board game comparable in game-tree complexity to chess and shogi. By analyzing over 10,000 records of human Xiangqi play, we highlight the existence of both transitive and non-transitive elements within the game's strategic structure. To address non-transitivity, we introduce the JiangJun algorithm, an innovative combination of Monte-Carlo Tree Search (MCTS) and Policy Space Response Oracles (PSRO) designed to approximate a Nash equilibrium. We evaluate the algorithm empirically using a WeChat mini program and achieve a Master level with a 99.41% win rate against human players. The algorithm's effectiveness in overcoming non-transitivity is confirmed by a plethora of metrics, such as relative population performance and visualization results. Our project site is available at https://sites.google.com/view/jiangjun-site/.

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in numerous applications. However, its practicality in addressing various real-world scenarios, characterized by diverse and unpredictable dynamics, noisy signals, and large state and action spaces, remains limited. This limitation stems from issues such as poor data efficiency, limited generalization capabilities, a lack of safety guarantees, and the absence of interpretability, among other factors. To overcome these challenges and improve performance across these crucial metrics, one promising avenue is to incorporate additional structural information about the problem into the RL learning process. Various sub-fields of RL have proposed methods for incorporating such inductive biases. We amalgamate these diverse methodologies under a unified framework, shedding light on the role of structure in the learning problem, and classify these methods into distinct patterns of incorporating structure. By leveraging this comprehensive framework, we provide valuable insights into the challenges of structured RL and lay the groundwork for a design pattern perspective on RL research. This novel perspective paves the way for future advancements and aids in developing more effective and efficient RL algorithms that can potentially handle real-world scenarios better.

Model-based reinforcement learning is a promising learning strategy for practical robotic applications due to its improved data-efficiency versus model-free counterparts. However, current state-of-the-art model-based methods rely on shaped reward signals, which can be difficult to design and implement. To remedy this, we propose a simple model-based method tailored for sparse-reward multi-goal tasks that foregoes the need for complicated reward engineering. This approach, termed Imaginary Hindsight Experience Replay, minimises real-world interactions by incorporating imaginary data into policy updates. To improve exploration in the sparse-reward setting, the policy is trained with standard Hindsight Experience Replay and endowed with curiosity-based intrinsic rewards. Upon evaluation, this approach provides an order of magnitude increase in data-efficiency on average versus the state-of-the-art model-free method in the benchmark OpenAI Gym Fetch Robotics tasks.

Reinforcement Learning (RL) provides a powerful framework for decision-making in complex environments. However, implementing RL in hardware-efficient and bio-inspired ways remains a challenge. This paper presents a novel Spiking Neural Network (SNN) architecture for solving RL problems with real-valued observations. The proposed model incorporates multi-layered event-based clustering, with the addition of Temporal Difference (TD)-error modulation and eligibility traces, building upon prior work. An ablation study confirms the significant impact of these components on the proposed model's performance. A tabular actor-critic algorithm with eligibility traces and a state-of-the-art Proximal Policy Optimization (PPO) algorithm are used as benchmarks. Our network consistently outperforms the tabular approach and successfully discovers stable control policies on classic RL environments: mountain car, cart-pole, and acrobot. The proposed model offers an appealing trade-off in terms of computational and hardware implementation requirements. The model does not require an external memory buffer nor a global error gradient computation, and synaptic updates occur online, driven by local learning rules and a broadcasted TD-error signal. Thus, this work contributes to the development of more hardware-efficient RL solutions.

We present a temporally layered architecture (TLA) for temporally adaptive control with minimal energy expenditure. The TLA layers a fast and a slow policy together to achieve temporal abstraction that allows each layer to focus on a different time scale. Our design draws on the energy-saving mechanism of the human brain, which executes actions at different timescales depending on the environment's demands. We demonstrate that beyond energy saving, TLA provides many additional advantages, including persistent exploration, fewer required decisions, reduced jerk, and increased action repetition. We evaluate our method on a suite of continuous control tasks and demonstrate the significant advantages of TLA over existing methods when measured over multiple important metrics. We also introduce a multi-objective score to qualitatively assess continuous control policies and demonstrate a significantly better score for TLA. Our training algorithm uses minimal communication between the slow and fast layers to train both policies simultaneously, making it viable for future applications in distributed control.

To use reinforcement learning from human feedback (RLHF) in practical applications, it is crucial to learn reward models from diverse sources of human feedback and to consider human factors involved in providing feedback of different types. However, the systematic study of learning from diverse types of feedback is held back by limited standardized tooling available to researchers. To bridge this gap, we propose RLHF-Blender, a configurable, interactive interface for learning from human feedback. RLHF-Blender provides a modular experimentation framework and implementation that enables researchers to systematically investigate the properties and qualities of human feedback for reward learning. The system facilitates the exploration of various feedback types, including demonstrations, rankings, comparisons, and natural language instructions, as well as studies considering the impact of human factors on their effectiveness. We discuss a set of concrete research opportunities enabled by RLHF-Blender. More information is available at https://rlhfblender.info/.

Reinforcement learning (RL) methods work in discrete time. In order to apply RL to inherently continuous problems like robotic control, a specific time discretization needs to be defined. This is a choice between sparse time control, which may be easier to train, and finer time control, which may allow for better ultimate performance. In this work, we propose SusACER, an off-policy RL algorithm that combines the advantages of different time discretization settings. Initially, it operates with sparse time discretization and gradually switches to a fine one. We analyze the effects of the changing time discretization in robotic control environments: Ant, HalfCheetah, Hopper, and Walker2D. In all cases our proposed algorithm outperforms state of the art.