Can humans get arbitrarily capable reinforcement learning (RL) agents to do their bidding? Or will sufficiently capable RL agents always find ways to bypass their intended objectives by shortcutting their reward signal? This question impacts how far RL can be scaled, and whether alternative paradigms must be developed in order to build safe artificial general intelligence. In this paper, we study when an RL agent has an instrumental goal to tamper with its reward process, and describe design principles that prevent instrumental goals for two different types of reward tampering (reward function tampering and RF-input tampering). Combined, the design principles can prevent both types of reward tampering from being instrumental goals. The analysis benefits from causal influence diagrams to provide intuitive yet precise formalizations.
How can we design agents that pursue a given objective when all feedback mechanisms are influenceable by the agent? Standard RL algorithms assume a secure reward function, and can thus perform poorly in settings where agents can tamper with the reward-generating mechanism. We present a principled solution to the problem of learning from influenceable feedback, which combines approval with a decoupled feedback collection procedure. For a natural class of corruption functions, decoupled approval algorithms have aligned incentives both at convergence and for their local updates. Empirically, they…
This paper describes REALab, a platform for embedded agency research in reinforcement learning (RL). REALab is designed to model the structure of tampering problems that may arise in real-world deployments of RL. Standard Markov Decision Process (MDP) formulations of RL and simulated environments mirroring the MDP structure assume secure access to feedback (e.g., rewards). This may be unrealistic in settings where agents are embedded and can corrupt the processes producing feedback (e.g., human supervisors, or an implemented reward function). We describe an alternative Corrupt Feedback MDP for…
Causal Information Prioritization for Efficient Reinforcement Learning
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
University of Tübingen（图宾根大学）；Technical University of Berlin（柏林工业大学）
In a sequential decision-making problem, having a structural dependency amongst the reward distributions associated with the arms makes it challenging to identify a subset of alternatives that guarantees the optimal collective outcome. Thus, besides individual actions' reward, learning the causal relations is essential to improve the decision-making strategy. To solve the two-fold learning problem described above, we develop the 'combinatorial semi-bandit framework with causally related rewards', where we model the causal relations by a directed graph in a stationary structural equation model.…
Indian Institute of Science（印度科学院）；Adobe Research（Adobe研究院）
We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on variables at each state. Generalizing the recent causal-bandit framework, the current work develops (simple) regret minimization guarantees for two-stage causal MDPs, with parallel causal graph at each state. We propose an algorithm that achieves an instance dependent regret bound. A key feature of our algorithm is that it utilizes convex optimization to address…
Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
Eindhoven University of Technology（埃因霍温理工大学）；University of California San Diego（加州大学圣迭戈分校）；University College London（伦敦大学学院）；University of Liverpool（利物浦大学）
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with $n$ time steps, a policy will make $n$ decisions on actions to take, many of which may appear non-intuitive to the observer. Moreover, it is not clear which of these decisions directly contribute towards achieving the reward and how significant is their contribution. Given a trained policy, we propose a black-box method based on counterfactual reasoning that estimates the causal effect that these decisions have on reward attainment and ranks the decisions according to this estimate…
WPI（伍斯特理工学院）；College of William & Mary（威廉与玛丽学院）；JD Finance（京东金融）；Didi Chuxing（滴滴出行）；Lenovo Group Limited（联想集团有限公司）
Many real-world human behaviors can be characterized as a sequential decision making processes, such as urban travelers choices of transport modes and routes (Wu et al. 2017). Differing from choices controlled by machines, which in general follows perfect rationality to adopt the policy with the highest reward, studies have revealed that human agents make sub-optimal decisions under bounded rationality (Tao, Rohde, and Corcoran 2014). Such behaviors can be modeled using maximum causal entropy (MCE) principle (Ziebart 2010). In this paper, we define and investigate a general reward trans-format…
A significant challenge in reinforcement learning is quantifying the complex relationship between actions and long-term rewards. The effects may manifest themselves over a long sequence of state-action pairs, making them hard to pinpoint. In this paper, we propose a method to link transitions with significant deviations in state with unusually large variations in subsequent rewards. Such transitions are marked as possible causal effects, and the corresponding state-action pairs are added to a separate replay buffer. In addition, we include \textit{contrastive} samples corresponding to transiti…
The combinatorial pure exploration of causal bandits is the following online learning task: given a causal graph with unknown causal inference distributions, in each round we choose a subset of variables to intervene or do no intervention, and observe the random outcomes of all random variables, with the goal that using as few rounds as possible, we can output an intervention that gives the best (or almost best) expected outcome on the reward variable $Y$ with probability at least $1-δ$, where $δ$ is a given confidence level. We provide the first gap-dependent and fully adaptive pure explorati…
Reinforcement learning is an appropriate and successful method to robustly perform low-level robot control under noisy conditions. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem down into a sequence of simpler high-level actions. A problem with the integration of both approaches is that action planning is based on discrete high-level action- and state spaces, whereas reinforcement learning is usually driven by a continuous reward function. However, recent advances in reinforcement learning, specifically, universal value function approx…
University of Tartu（塔尔图大学）；Institute of Computer Science（计算机科学研究所）
Exploration and credit assignment under sparse rewards are still challenging problems. We argue that these challenges arise in part due to the intrinsic rigidity of operating at the level of actions. Actions can precisely define how to perform an activity but are ill-suited to describe what activity to perform. Instead, causal effects are inherently composable and temporally abstract, making them ideal for descriptive tasks. By leveraging a hierarchy of causal effects, this study aims to expedite the learning of task-specific behavior and aid exploration. Borrowing counterfactual and normality…
Inverse Reinforcement Learning (IRL) algorithms infer a reward function that explains demonstrations provided by an expert acting in the environment. Maximum Causal Entropy (MCE) IRL is currently the most popular formulation of IRL, with numerous extensions. In this tutorial, we present a compressed derivation of MCE IRL and the key results from contemporary implementations of MCE IRL algorithms. We hope this will serve both as an introductory resource for those new to the field, and as a concise reference for those already familiar with these topics.
When learning a task as a team, some agents in Multi-Agent Reinforcement Learning (MARL) may fail to understand their true impact in the performance of the team. Such agents end up learning sub-optimal policies, demonstrating undesired lazy behaviours. To investigate this problem, we start by formalising the use of temporal causality applied to MARL problems. We then show how causality can be used to penalise such lazy agents and improve their behaviours. By understanding how their local observations are causally related to the team reward, each agent in the team can adjust their individual cr…
Columbia University（哥伦比亚大学）；Purdue University（普渡大学）
One of the common ways children learn is by mimicking adults. Imitation learning focuses on learning policies with suitable performance from demonstrations generated by an expert, with an unspecified performance measure, and unobserved reward signal. Popular methods for imitation learning start by either directly mimicking the behavior policy of an expert (behavior cloning) or by learning a reward function that prioritizes observed expert trajectories (inverse reinforcement learning). However, these methods rely on the assumption that covariates used by the expert to determine her/his actions …
In online recommendation, customers arrive in a sequential and stochastic manner from an underlying distribution and the online decision model recommends a chosen item for each arriving individual based on some strategy. We study how to recommend an item at each step to maximize the expected reward while achieving user-side fairness for customers, i.e., customers who share similar profiles will receive a similar reward regardless of their sensitive attributes and items being recommended. By incorporating causal inference into bandits and adopting soft intervention to model the arm selection st…
Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State
RWTH Aachen University（亚琛工业大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；The University of Tokyo（东京大学）；The Hong Kong University of Science and Technology（香港科技大学）
Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Alberta（阿尔伯塔大学）；Tübingen AI Center（图宾根人工智能中心）；ELLIS Institute（ELLIS研究所）；Technische Universität Braunschweig（不伦瑞克工业大学）
Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals
College of Computer and Cyber Security, Fujian Normal University（福建师范大学计算机与网络空间安全学院）；Fujian Provincial Key Laboratory of Network Security and Cryptology（福建省网络安全与密码技术重点实验室）
Although it is well known that exploration plays a key role in Reinforcement Learning (RL), prevailing exploration strategies for continuous control tasks in RL are mainly based on naive isotropic Gaussian noise regardless of the causality relationship between action space and the task and consider all dimensions of actions equally important. In this work, we propose to conduct interventions on the primal action space to discover the causal relationship between the action space and the task reward. We propose the method of State-Wise Action Refined (SWAR), which addresses the issue of action s…
Agents are systems that optimize an objective function in an environment. Together, the goal and the environment induce secondary objectives, incentives. Modeling the agent-environment interaction using causal influence diagrams, we can answer two fundamental questions about an agent's incentives directly from the graph: (1) which nodes can the agent have an incentivize to observe, and (2) which nodes can the agent have an incentivize to control? The answers tell us which information and influence points need extra protection. For example, we may want a classifier for job applications to not u…
City University of Hong Kong（香港城市大学）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Amsterdam（阿姆斯特丹大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Dealing with non-stationarity in environments (e.g., in the transition dynamics) and objectives (e.g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). While most current approaches model the changes as a single shared embedding vector, we leverage insights from the recent causality literature to model non-stationarity in terms of individual latent change factors, and causal graphs across different environments. In particular, we propose Factored Adaptation for Non-Stationary RL (FANS-RL), a factored adaption approach …
In this paper, we study a transfer reinforcement learning problem where the state transitions and rewards are affected by the environmental context. Specifically, we consider a demonstrator agent that has access to a context-aware policy and can generate transition and reward data based on that policy. These data constitute the experience of the demonstrator. Then, the goal is to transfer this experience, excluding the underlying contextual information, to a learner agent that does not have access to the environmental context, so that they can learn a control policy using fewer samples. It is …
Shandong University（山东大学）；Suzhou University of Science and Technology（苏州科技大学）；Beijing University of Civil Engineering and Architecture（北京建筑大学）
Learning directed acyclic graph (DAG) that describes the causality of observed data is a very challenging but important task. Due to the limited quantity and quality of observed data, and non-identifiability of causal graph, it is almost impossible to infer a single precise DAG. Some methods approximate the posterior distribution of DAGs to explore the DAG space via Markov chain Monte Carlo (MCMC), but the DAG space is over the nature of super-exponential growth, accurately characterizing the whole distribution over DAGs is very intractable. In this paper, we propose {Reinforcement Causal Stru…
Demonstration is an appealing way for humans to provide assistance to reinforcement-learning agents. Most approaches in this area view demonstrations primarily as sources of behavioral bias. But in sparse-reward tasks, humans seem to treat demonstrations more as sources of causal knowledge. This paper proposes a framework for agents that benefit from demonstration in this human-inspired way. In this framework, agents develop causal models through observation, and reason from this knowledge to decompose tasks for effective reinforcement learning. Experimental results show that a basic implement…
