Successor-style representations have many advantages for reinforcement learning: for example, they can help an agent generalize from past experience to new goals, and they have been proposed as explanations of behavioral and neural data from human and animal learners. They also form a natural bridge between model-based and model-free RL methods: like the former they make predictions about future experiences, and like the latter they allow efficient prediction of total discounted rewards. However, successor-style representations are not optimized to generalize across policies: typically, we maintain a limited-length list of policies, and share information among them by representation learning or GPI. Successor-style representations also typically make no provision for gathering information or reasoning about latent variables. To address these limitations, we bring together ideas from predictive state representations, belief space value iteration, successor features, and convex analysis: we develop a new, general successor-style representation, together with a Bellman equation that connects multiple sources of information within this representation, including different latent states, policies, and reward functions. The new representation is highly expressive: for example, it lets us efficiently read off an optimal policy for a new reward function, or a policy that imitates a new demonstration. For this paper, we focus on exact computation of the new representation in small, known environments, since even this restricted setting offers plenty of interesting questions. Our implementation does not scale to large, unknown environments -- nor would we expect it to, since it generalizes POMDP value iteration, which is difficult to scale. However, we believe that future work will allow us to extend our ideas to approximate reasoning in large, unknown environments.
National University of Singapore（新加坡国立大学）；Smart Systems Institute (SSI), NUS（新加坡国立大学智能系统研究所（SSI））
In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints. This problem is important for safety-critical applications where interactions are costly and unconstrained policies can lead to undesirable or dangerous outcomes, e.g., with physical robots that interact with humans. We propose a Constrained Markov Decision Process (CMDP) formulation that simultaneously enables the transfer of policies and adherence to safety constraints. Our formulation cleanly separates task goals …
Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer, hierarchy, and robustness. We propose Diverse Successive Policies, a method for discovering policies that are diverse in the space of Successor Features, while assuring that they are near optimal. We formalize the problem as a Constrained Markov Decision Process (CMDP) where the goal is to find policies that maximize diversity, characterized by an intrinsic div…
Institute of Informatics, Federal University of Rio Grande do Sul（南里奥格兰德联邦大学信息学研究所）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
In many real-world applications, reinforcement learning (RL) agents might have to solve multiple tasks, each one typically modeled via a reward function. If reward functions are expressed linearly, and the agent has previously learned a set of policies for different tasks, successor features (SFs) can be exploited to combine such policies and identify reasonable solutions for new problems. However, the identified solutions are not guaranteed to be optimal. We introduce a novel algorithm that addresses this limitation. It allows RL agents to combine existing policies and directly identify optim…
A major challenge in reinforcement learning (RL) is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcement learning, which identifies common structures among past tasks to be then generalized to new tasks (meta-test). In meta-training, the RL agent learns state representations that encode prior information from a set of tasks, used to generalize the value function approximation. This has been proposed in the literature as successor representation approximators. While promising, these methods do not generalize well acros…
Constrained Reinforcement Learning Using Successor Representations
Technical University of Darmstadt (TU Darmstadt)（达姆施塔特工业大学）；Hessian Center for Artificial Intelligence (hessian.AI)（黑森州人工智能中心）；Fraunhofer Institute for Integrated Circuits IIS, Fraunhofer IIS（弗劳恩霍夫集成电路研究所IIS）；University of Technology Nuremberg (UTN)（纽伦堡工业大学）
We present a temporally extended variation of the successor representation, which we term t-SR. t-SR captures the expected state transition dynamics of temporally extended actions by constructing successor representations over primitive action repeats. This form of temporal abstraction does not learn a top-down hierarchy of pertinent task structures, but rather a bottom-up composition of coupled actions and action repetitions. This lessens the amount of decisions required in control without learning a hierarchical policy. As such, t-SR directly considers the time horizon of temporally extended…
Vector Institute（向量研究所）；University of Toronto（多伦多大学）；DeepMind（深度思维）
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer learning and the latter by optimizing some utility function of the return. However, the problem of transferring skills in a risk-aware manner is not well-understood. In this paper, we address the problem of risk-aware policy transfer between tasks in a common domain that differ only in their reward functions, in which risk is measured by the variance of reward streams. Our approach begins by extending the idea of gener…
Brown University（布朗大学）；Computer Science Department（计算机科学系）；Carney Institute for Brain Science（卡尼脑科学研究所）；Providence, RI 02912, USA（美国罗得岛州普罗维登斯市 02912）
A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs. By generalizing across different inputs, information learned for one input can be immediately reused for improving predictions for another input. Reusing information allows an agent to compute an optimal decision-making strategy using less data. State representation is a key element of the generalization process, compressing a high-dimensional input space into a low-dimensional latent state space. This article analyzes properties of different latent state spaces, leading to ne…
University of Oxford（牛津大学）；University of Vienna（维也纳大学）
Abstraction plays an important role in the generalisation of knowledge and skills and is key to sample efficient learning. In this work, we study joint temporal and state abstraction in reinforcement learning, where temporally-extended actions in the form of options induce temporal abstractions, while aggregation of similar states with respect to abstract options induces state abstractions. Many existing abstraction schemes ignore the interplay of state and temporal abstraction. Consequently, the considered option policies often cannot be directly transferred to new environments due to changes…
The options framework in reinforcement learning models the notion of a skill or a temporally extended sequence of actions. The discovery of a reusable set of skills has typically entailed building options, that navigate to bottleneck states. This work adopts a complementary approach, where we attempt to discover options that navigate to landmark states. These states are prototypical representatives of well-connected regions and can hence access the associated region with relative ease. In this work, we propose Successor Options, which leverages Successor Representations to build a model of the…
University of Science and Technology of China（中国科学技术大学）
Most reinforcement learning (RL) methods only focus on learning a single task from scratch and are not able to use prior knowledge to learn other tasks more effectively. Context-based meta RL techniques are recently proposed as a possible solution to tackle this. However, they are usually less efficient than conventional RL and may require many trial-and-errors during training. To address this, we propose a novel meta-RL approach that achieves competitive performance comparing to existing meta-RL algorithms, while requires significantly fewer environmental interactions. By combining context va…
It has been established that diverse behaviors spanning the controllable subspace of an Markov decision process can be trained by rewarding a policy for being distinguishable from other policies \citep{gregor2016variational, eysenbach2018diversity, warde2018unsupervised}. However, one limitation of this formulation is generalizing behaviors beyond the finite set being explicitly learned, as is needed for use on subsequent tasks. Successor features \citep{dayan93improving, barreto2017successor} provide an appealing solution to this generalization problem, but require defining the reward functio…
Deep Reinforcement Learning has been very successful recently with various works on complex domains. Most works are concerned with learning a single policy that solves the target task, but is fixed in the sense that if the environment changes the agent is unable to adapt to it. Successor Features (SFs) proposes a mechanism that allows learning policies that are not tied to any particular reward function. In this work we investigate how SFs may be pre-trained without observing any reward in a custom environment that features resource collection, traps and crafting. After pre-training we expose …
The ability to transfer skills across tasks has the potential to scale up reinforcement learning (RL) agents to environments currently out of reach. Recently, a framework based on two ideas, successor features (SFs) and generalised policy improvement (GPI), has been introduced as a principled way of transferring skills. In this paper we extend the SFs & GPI framework in two ways. One of the basic assumptions underlying the original formulation of SFs & GPI is that rewards for all tasks of interest can be computed as linear combinations of a fixed set of features. We relax this constraint and s…
Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another. Furthermore, many of such skills are acquired without explicit supervision in an intrinsically driven fashion. This is in contrast to the state-of-the-art reinforcement learning agents, which typically start learning each new task from scratch and struggle with knowledge transfer. In this paper we propose a principled way to learn a basis set of policies, which, when recombined through generalised policy improvement, come with guarantees on t…
Gatsby Computational Neuroscience Unit（盖茨比计算神经科学研究组）；University College London（伦敦大学学院）
Animals need to devise strategies to maximize returns while interacting with their environment based on incoming noisy sensory observations. Task-relevant states, such as the agent's location within an environment or the presence of a predator, are often not directly observable but must be inferred using available sensory information. Successor representations (SR) have been proposed as a middle-ground between model-based and model-free reinforcement learning strategies, allowing for fast value computation and rapid adaptation to changes in the reward function or goal locations. Indeed, recent…
Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning
Harbin Institute of Technology（哈尔滨工业大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Northwestern Polytechnical University（西北工业大学）；Shenzhen Research Institute of Northwestern Polytechnical University（西北工业大学深圳研究院）
University of Oxford（牛津大学）；University of California, Berkeley（加州大学伯克利分校）；Google Research（谷歌研究院）；DeepMind（深度思维）
We study reinforcement learning (RL) with no-reward demonstrations, a setting in which an RL agent has access to additional data from the interaction of other agents with the same environment. However, it has no access to the rewards or goals of these agents, and their objectives and levels of expertise may vary widely. These assumptions are common in multi-agent settings, such as autonomous driving. To effectively use this data, we turn to the framework of successor features. This allows us to disentangle shared features and dynamics of the environment from agent-specific rewards and policies…
Learning personalized decision policies that generalize to the target population is of great relevance. Since training data is often not representative of the target population, standard policy learning methods may yield policies that do not generalize target population. To address this challenge, we propose a novel framework for learning policies that generalize to the target population. For this, we characterize the difference between the training data and the target population as a sample selection bias using a selection variable. Over an uncertainty set around this selection variable, we o…
The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills. We focus on one aspect in particular, namely the ability to generalise to unseen tasks. Parametric generalisation relies on the interpolation power of a function approximator that is given the task description as input; one of its most common form are universal value function approximators (UVFAs). Another way to generalise to new tas…
University of Michigan（密歇根大学）；LG AI Research（LG人工智能研究院）
Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-conditioned reinforcement learning (GCRL), becomes especially challenging for long-horizon goals. Current methods have tackled this problem by augmenting goal-conditioned policies with graph-based planning algorithms. However, they struggle to scale to large, high-dimensional state spaces and assume access to exploration mechanisms for efficiently collecting training data. In this work, we introduce Successor Feature Land…
Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. However, it is non-trivial to manually design a robot controller that combines modalities with very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. We use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our po…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
To perform manipulation tasks in the real world, robots need to operate on objects with various shapes, sizes and without access to geometric models. It is often unfeasible to train monolithic neural network policies across such large variance in object properties. Towards this generalization challenge, we propose to learn modular task policies which compose object-centric task-axes controllers. These task-axes controllers are parameterized by properties associated with underlying objects in the scene. We infer these controller parameters directly from visual input using multi-view dense corre…
In multi-agent reinforcement learning, the inherent non-stationarity of the environment caused by other agents' actions posed significant difficulties for an agent to learn a good policy independently. One way to deal with non-stationarity is opponent modeling, by which the agent takes into consideration the influence of other agents' policies. Most existing work relies on predicting other agents' actions or goals, or discriminating between different policies. However, such modeling fails to capture the similarities and differences between policies simultaneously and thus cannot provide enough…
Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learning algorithm. The advantage is that the algorithm can then use the reward function to check the reward for states that the agent hasn't even encountered yet. In addition, the algorithm can simultaneously learn policies for multiple reward functions. For each state, the algorithm…
