Hindsight experience replay (HER) accelerates off-policy reinforcement learning algorithms for environments that emit sparse rewards by modifying the goal of the episode post-hoc to be some state achieved during the episode. Because post-hoc modification of the observed goal violates the assumptions of on-policy algorithms, HER is not typically applied to on-policy algorithms. Here, we show that HER can dramatically accelerate proximal policy optimization (PPO), an on-policy reinforcement learning algorithm, when tested on a custom predator-prey environment.

Mission-oriented drone networks have been widely used for structural inspection, disaster monitoring, border surveillance, etc. Due to the limited battery capacity of drones, mission execution strategy impacts network performance and mission completion. However, collaborative execution is a challenging problem for drones in such a dynamic environment as it also involves efficient trajectory design. We leverage multi-agent reinforcement learning (MARL) to manage the challenge in this study, letting each drone learn to collaboratively execute tasks and plan trajectories based on its current status and environment. Simulation results show that the proposed collaborative execution model can successfully complete the mission at least 80% of the time, regardless of task locations and lengths, and can even achieve a 100% success rate when the task density is not way too sparse. To the best of our knowledge, our work is one of the pioneer studies on leveraging MARL on collaborative execution for mission-oriented drone networks; the unique value of this work lies in drone battery level driving our model design.

As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic outcomes. This paper experimentally evaluates and compares the effectiveness of future action and event prediction for three types of RL agents: explicitly planning, implicitly planning, and non-planning. We employ two approaches: the inner state approach, which involves predicting based on the inner computations of the agents (e.g., plans or neuron activations), and a simulation-based approach, which involves unrolling the agent in a learned world model. Our results show that the plans of explicitly planning agents are significantly more informative for prediction than the neuron activations of the other types. Furthermore, using internal plans proves more robust to model quality compared to simulation-based approaches when predicting actions, while the results for event prediction are more mixed. These findings highlight the benefits of leveraging inner states and simulations to predict future agent actions and events, thereby improving interaction and safety in real-world deployments.

Aligning AI agents with human values is challenging due to diverse and subjective notions of values. Standard alignment methods often aggregate crowd feedback, which can result in the suppression of unique or minority preferences. We introduce Interactive-Reflective Dialogue Alignment, a method that iteratively engages users in reflecting on and specifying their subjective value definitions. This system learns individual value definitions through language-model-based preference elicitation and constructs personalized reward models that can be used to align AI behaviour. We evaluated our system through two studies with 30 participants, one focusing on "respect" and the other on ethical decision-making in autonomous vehicles. Our findings demonstrate diverse definitions of value-aligned behaviour and show that our system can accurately capture each person's unique understanding. This approach enables personalized alignment and can inform more representative and interpretable collective alignment strategies.

With Deep Reinforcement Learning (DRL) being increasingly considered for the control of real-world systems, the lack of transparency of the neural network at the core of RL becomes a concern. Programmatic Reinforcement Learning (PRL) is able to to create representations of this black-box in the form of source code, not only increasing the explainability of the controller but also allowing for user adaptations. However, these methods focus on distilling a black-box policy into a program and do so after learning using the Mean Squared Error between produced and wanted behaviour, discarding other elements of the RL algorithm. The distilled policy may therefore perform significantly worse than the black-box learned policy. In this paper, we propose to directly learn a program as the policy of an RL agent. We build on TD3 and use its critics as the basis of the objective function of a genetic algorithm that syntheses the program. Our approach builds the program during training, as opposed to after the fact. This steers the program to actual high rewards, instead of a simple Mean Squared Error. Also, our approach leverages the TD3 critics to achieve high sample-efficiency, as opposed to pure genetic methods that rely on Monte-Carlo evaluations. Our experiments demonstrate the validity, explainability and sample-efficiency of our approach in a simple gridworld environment.

With high-dimensional state spaces, visual reinforcement learning (RL) faces significant challenges in exploitation and exploration, resulting in low sample efficiency and training stability. As a time-efficient diffusion model, although consistency models have been validated in online state-based RL, it is still an open question whether it can be extended to visual RL. In this paper, we investigate the impact of non-stationary distribution and the actor-critic framework on consistency policy in online RL, and find that consistency policy was unstable during the training, especially in visual RL with the high-dimensional state space. To this end, we suggest sample-based entropy regularization to stabilize the policy training, and propose a consistency policy with prioritized proximal experience regularization (CP3ER) to improve sample efficiency. CP3ER achieves new state-of-the-art (SOTA) performance in 21 tasks across DeepMind control suite and Meta-world. To our knowledge, CP3ER is the first method to apply diffusion/consistency models to visual RL and demonstrates the potential of consistency models in visual RL. More visualization results are available at https://jzndd.github.io/CP3ER-Page/.

Current reinforcement-learning methods are unable to directly learn policies that solve the minimum cost reach-avoid problem to minimize cumulative costs subject to the constraints of reaching the goal and avoiding unsafe states, as the structure of this new optimization problem is incompatible with current methods. Instead, a surrogate problem is solved where all objectives are combined with a weighted sum. However, this surrogate objective results in suboptimal policies that do not directly minimize the cumulative cost. In this work, we propose RC-PPO, a reinforcement-learning-based method for solving the minimum-cost reach-avoid problem by using connections to Hamilton-Jacobi reachability. Empirical results demonstrate that RC-PPO learns policies with comparable goal-reaching rates to while achieving up to 57% lower cumulative costs compared to existing methods on a suite of minimum-cost reach-avoid benchmarks on the Mujoco simulator. The project page can be found at https://oswinso.xyz/rcppo/.

Reinforcement learning (RL) has achieved outstanding success in complex robot control tasks, such as drone racing, where the RL agents have outperformed human champions in a known racing track. However, these agents fail in unseen track configurations, always requiring complete retraining when presented with new track layouts. This work aims to develop RL agents that generalize effectively to novel track configurations without retraining. The naive solution of training directly on a diverse set of track layouts can overburden the agent, resulting in suboptimal policy learning as the increased complexity of the environment impairs the agent's ability to learn to fly. To enhance the generalizability of the RL agent, we propose an adaptive environment-shaping framework that dynamically adjusts the training environment based on the agent's performance. We achieve this by leveraging a secondary RL policy to design environments that strike a balance between being challenging and achievable, allowing the agent to adapt and improve progressively. Using our adaptive environment shaping, one single racing policy efficiently learns to race in diverse challenging tracks. Experimental results validated in both simulation and the real world show that our method enables drones to successfully fly complex and unseen race tracks, outperforming existing environment-shaping techniques. Project page: http://rpg.ifi.uzh.ch/env_as_policy/index.html

The Transformer model has demonstrated success across a wide range of domains, including in Multi-Agent Reinforcement Learning (MARL) where the Multi-Agent Transformer (MAT) has emerged as a leading algorithm in the field. However, a significant drawback of Transformer models is their quadratic computational complexity relative to input size, making them computationally expensive when scaling to larger inputs. This limitation restricts MAT's scalability in environments with many agents. Recently, State-Space Models (SSMs) have gained attention due to their computational efficiency, but their application in MARL remains unexplored. In this work, we investigate the use of Mamba, a recent SSM, in MARL and assess whether it can match the performance of MAT while providing significant improvements in efficiency. We introduce a modified version of MAT that incorporates standard and bi-directional Mamba blocks, as well as a novel "cross-attention" Mamba block. Extensive testing shows that our Multi-Agent Mamba (MAM) matches the performance of MAT across multiple standard multi-agent environments, while offering superior scalability to larger agent scenarios. This is significant for the MARL community, because it indicates that SSMs could replace Transformers without compromising performance, whilst also supporting more effective scaling to higher numbers of agents. Our project page is available at https://sites.google.com/view/multi-agent-mamba .

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right balance between task performance and constraint satisfaction and it is prone for them to get stuck in over-conservative or constraint violating local minima. In this paper, we propose Adversarial Constrained Policy Optimization (ACPO), which enables simultaneous optimization of reward and the adaptation of cost budgets during training. Our approach divides original constrained problem into two adversarial stages that are solved alternately, and the policy update performance of our algorithm can be theoretically guaranteed. We validate our method through experiments conducted on Safety Gymnasium and quadruped locomotion tasks. Results demonstrate that our algorithm achieves better performances compared to commonly used baselines.