Volodymyr Mnih

Michael Laskin, Luyu Wang, Junhyuk Oh et al.

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to reinforcement learn as an across-episode sequential prediction problem. A dataset of learning histories is generated by a source RL algorithm, and then a causal transformer is trained by autoregressively predicting actions given their preceding learning histories as context. Unlike sequential policy prediction architectures that distill post-learning or expert sequences, AD is able to improve its policy entirely in-context without updating its network parameters. We demonstrate that AD can reinforcement learn in-context in a variety of environments with sparse rewards, combinatorial task structure, and pixel-based observations, and find that AD learns a more data-efficient RL algorithm than the one that generated the source data.

SIMA team, Adrian Bolton, Alexander Lerchner et al.

We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a significant step toward active, goal-directed interaction within an embodied environment. Unlike prior work (e.g., SIMA 1) limited to simple language commands, SIMA 2 acts as an interactive partner, capable of reasoning about high-level goals, conversing with the user, and handling complex instructions given through language and images. Across a diverse portfolio of games, SIMA 2 substantially closes the gap with human performance and demonstrates robust generalization to previously unseen environments, all while retaining the base model's core reasoning capabilities. Furthermore, we demonstrate a capacity for open-ended self-improvement: by leveraging Gemini to generate tasks and provide rewards, SIMA 2 can autonomously learn new skills from scratch in a new environment. This work validates a path toward creating versatile and continuously learning agents for both virtual and, eventually, physical worlds.

Hao Liu, Tom Zahavy, Volodymyr Mnih et al.

Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the environment, which changes the input sensory signals and the state of the environment. In this work, we aim to bring the best of both worlds and propose an algorithm that exhibits an exploratory behavior whilst it utilizes large diverse datasets. Our key idea is to leverage deep generative models that are pretrained on static datasets and introduce a dynamic model in the latent space. The transition dynamics simply mixes an action and a random sampled latent. It then applies an exponential moving average for temporal persistency, the resulting latent is decoded to image using pretrained generator. We then employ an unsupervised reinforcement learning algorithm to explore in this environment and perform unsupervised representation learning on the collected data. We further leverage the temporal information of this data to pair data points as a natural supervision for representation learning. Our experiments suggest that the learned representations can be successfully transferred to downstream tasks in both vision and reinforcement learning domains.

Anian Ruoss, Fabio Pardo, Harris Chan et al.

In this paper, we present a benchmark to pressure-test today's frontier models' multimodal decision-making capabilities in the very long-context regime (up to one million tokens) and investigate whether these models can learn from large numbers of expert demonstrations in their context. We evaluate the performance of Claude 3.5 Sonnet, Gemini 1.5 Flash, Gemini 1.5 Pro, Gemini 2.0 Flash Experimental, GPT-4o, o1-mini, o1-preview, and o1 as policies across a battery of simple interactive decision-making tasks: playing tic-tac-toe, chess, and Atari, navigating grid worlds, solving crosswords, and controlling a simulated cheetah. We study increasing amounts of expert demonstrations in the context $\unicode{x2013}$ from no demonstrations to 512 full episodes. Across our tasks, models rarely manage to fully reach expert performance, and often, presenting more demonstrations has little effect. Some models steadily improve with more demonstrations on a few tasks. We investigate the effect of encoding observations as text or images and the impact of chain-of-thought prompting. To help quantify the impact of other approaches and future innovations, we open source our benchmark that covers the zero-, few-, and many-shot regimes in a unified evaluation.

Kate Baumli, Satinder Baveja, Feryal Behbahani et al. · oxford

Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning. A key limiting factor for building generalist agents with RL has been the need for a large number of reward functions for achieving different goals. We investigate the feasibility of using off-the-shelf vision-language models, or VLMs, as sources of rewards for reinforcement learning agents. We show how rewards for visual achievement of a variety of language goals can be derived from the CLIP family of models, and used to train RL agents that can achieve a variety of language goals. We showcase this approach in two distinct visual domains and present a scaling trend showing how larger VLMs lead to more accurate rewards for visual goal achievement, which in turn produces more capable RL agents.

Ishan Durugkar, Steven Hansen, Stephen Spencer et al.

This paper deals with the problem of learning a skill-conditioned policy that acts meaningfully in the absence of a reward signal. Mutual information based objectives have shown some success in learning skills that reach a diverse set of states in this setting. These objectives include a KL-divergence term, which is maximized by visiting distinct states even if those states are not far apart in the MDP. This paper presents an approach that rewards the agent for learning skills that maximize the Wasserstein distance of their state visitation from the start state of the skill. It shows that such an objective leads to a policy that covers more distance in the MDP than diversity based objectives, and validates the results on a variety of Atari environments.

Tom Zahavy, Brendan O'Donoghue, Andre Barreto et al.

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 diversity reward, while remaining near-optimal with respect to the extrinsic reward of the MDP. We also analyze how recently proposed robustness and discrimination rewards perform and find that they are sensitive to the initialization of the procedure and may converge to sub-optimal solutions. To alleviate this, we propose new explicit diversity rewards that aim to minimize the correlation between the Successor Features of the policies in the set. We compare the different diversity mechanisms in the DeepMind Control Suite and find that the type of explicit diversity we are proposing is important to discover distinct behavior, like for example different locomotion patterns.

Kate Baumli, David Warde-Farley, Steven Hansen et al.

In the absence of external rewards, agents can still learn useful behaviors by identifying and mastering a set of diverse skills within their environment. Existing skill learning methods use mutual information objectives to incentivize each skill to be diverse and distinguishable from the rest. However, if care is not taken to constrain the ways in which the skills are diverse, trivially diverse skill sets can arise. To ensure useful skill diversity, we propose a novel skill learning objective, Relative Variational Intrinsic Control (RVIC), which incentivizes learning skills that are distinguishable in how they change the agent's relationship to its environment. The resulting set of skills tiles the space of affordances available to the agent. We qualitatively analyze skill behaviors on multiple environments and show how RVIC skills are more useful than skills discovered by existing methods when used in hierarchical reinforcement learning.

Tom Van de Wiele, David Warde-Farley, Andriy Mnih et al.

Applying Q-learning to high-dimensional or continuous action spaces can be difficult due to the required maximization over the set of possible actions. Motivated by techniques from amortized inference, we replace the expensive maximization over all actions with a maximization over a small subset of possible actions sampled from a learned proposal distribution. The resulting approach, which we dub Amortized Q-learning (AQL), is able to handle discrete, continuous, or hybrid action spaces while maintaining the benefits of Q-learning. Our experiments on continuous control tasks with up to 21 dimensional actions show that AQL outperforms D3PG (Barth-Maron et al, 2018) and QT-Opt (Kalashnikov et al, 2018). Experiments on structured discrete action spaces demonstrate that AQL can efficiently learn good policies in spaces with thousands of discrete actions.

Tejas Kulkarni, Ankush Gupta, Catalin Ionescu et al.

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and reinforcement learning (RL). To this end, we introduce Transporter, a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space coordinates. Our method learns from raw video frames in a fully unsupervised manner, by transporting learnt image features between video frames using a keypoint bottleneck. The discovered keypoints track objects and object parts across long time-horizons more accurately than recent similar methods. Furthermore, consistent long-term tracking enables two notable results in control domains -- (1) using the keypoint co-ordinates and corresponding image features as inputs enables highly sample-efficient reinforcement learning; (2) learning to explore by controlling keypoint locations drastically reduces the search space, enabling deep exploration (leading to states unreachable through random action exploration) without any extrinsic rewards.

Steven Hansen, Will Dabney, Andre Barreto et al.

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 function as linear in some grounded feature space. In this paper, we show that these two techniques can be combined, and that each method solves the other's primary limitation. To do so we introduce Variational Intrinsic Successor FeatuRes (VISR), a novel algorithm which learns controllable features that can be leveraged to provide enhanced generalization and fast task inference through the successor feature framework. We empirically validate VISR on the full Atari suite, in a novel setup wherein the rewards are only exposed briefly after a long unsupervised phase. Achieving human-level performance on 14 games and beating all baselines, we believe VISR represents a step towards agents that rapidly learn from limited feedback.

David Warde-Farley, Tom Van de Wiele, Tejas Kulkarni et al.

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. Our agent simultaneously learns a goal-conditioned policy and a goal achievement reward function that measures how similar a state is to the goal state. This dual optimization leads to a co-operative game, giving rise to a learned reward function that reflects similarity in controllable aspects of the environment instead of distance in the space of observations. We demonstrate the efficacy of our agent to learn, in an unsupervised manner, to reach a diverse set of goals on three domains -- Atari, the DeepMind Control Suite and DeepMind Lab.

Martin Riedmiller, Roland Hafner, Thomas Lampe et al.

We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several challenging robotic manipulation settings demonstrate the power of our approach.

Brendan O'Donoghue, Ian Osband, Remi Munos et al.

We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar \textit{uncertainty} Bellman equation (UBE), which connects the uncertainty at any time-step to the expected uncertainties at subsequent time-steps, thereby extending the potential exploratory benefit of a policy beyond individual time-steps. We prove that the unique fixed point of the UBE yields an upper bound on the variance of the posterior distribution of the Q-values induced by any policy. This bound can be much tighter than traditional count-based bonuses that compound standard deviation rather than variance. Importantly, and unlike several existing approaches to optimism, this method scales naturally to large systems with complex generalization. Substituting our UBE-exploration strategy for $ε$-greedy improves DQN performance on 51 out of 57 games in the Atari suite.

Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki et al.

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupervised learning, continues to develop in the absence of extrinsic rewards. We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt to the most relevant aspects of the actual task. Our agent significantly outperforms the previous state-of-the-art on Atari, averaging 880\% expert human performance, and a challenging suite of first-person, three-dimensional \emph{Labyrinth} tasks leading to a mean speedup in learning of 10$\times$ and averaging 87\% expert human performance on Labyrinth.

Brendan O'Donoghue, Remi Munos, Koray Kavukcuoglu et al.

Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experience from a replay buffer. This is motivated by making a connection between the fixed points of the regularized policy gradient algorithm and the Q-values. This connection allows us to estimate the Q-values from the action preferences of the policy, to which we apply Q-learning updates. We refer to the new technique as 'PGQL', for policy gradient and Q-learning. We also establish an equivalency between action-value fitting techniques and actor-critic algorithms, showing that regularized policy gradient techniques can be interpreted as advantage function learning algorithms. We conclude with some numerical examples that demonstrate improved data efficiency and stability of PGQL. In particular, we tested PGQL on the full suite of Atari games and achieved performance exceeding that of both asynchronous advantage actor-critic (A3C) and Q-learning.

Ziyu Wang, Victor Bapst, Nicolas Heess et al.

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems. To achieve this, the paper introduces several innovations, including truncated importance sampling with bias correction, stochastic dueling network architectures, and a new trust region policy optimization method.

Jimmy Ba, Geoffrey Hinton, Volodymyr Mnih et al.

Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this restriction. Synapses have dynamics at many different time-scales and this suggests that artificial neural networks might benefit from variables that change slower than activities but much faster than the standard weights. These "fast weights" can be used to store temporary memories of the recent past and they provide a neurally plausible way of implementing the type of attention to the past that has recently proved very helpful in sequence-to-sequence models. By using fast weights we can avoid the need to store copies of neural activity patterns.

Alexander, Vezhnevets, Volodymyr Mnih et al.

We present a novel deep recurrent neural network architecture that learns to build implicit plans in an end-to-end manner by purely interacting with an environment in reinforcement learning setting. The network builds an internal plan, which is continuously updated upon observation of the next input from the environment. It can also partition this internal representation into contiguous sub- sequences by learning for how long the plan can be committed to - i.e. followed without re-planing. Combining these properties, the proposed model, dubbed STRategic Attentive Writer (STRAW) can learn high-level, temporally abstracted macro- actions of varying lengths that are solely learnt from data without any prior information. These macro-actions enable both structured exploration and economic computation. We experimentally demonstrate that STRAW delivers strong improvements on several ATARI games by employing temporally extended planning strategies (e.g. Ms. Pacman and Frostbite). It is at the same time a general algorithm that can be applied on any sequence data. To that end, we also show that when trained on text prediction task, STRAW naturally predicts frequent n-grams (instead of macro-actions), demonstrating the generality of the approach.

Hado van Hasselt, Arthur Guez, Matteo Hessel et al.

Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the policy of behavior. Our main motivation is prior work on learning to play Atari games, where the rewards were all clipped to a predetermined range. This clipping facilitates learning across many different games with a single learning algorithm, but a clipped reward function can result in qualitatively different behavior. Using the adaptive normalization we can remove this domain-specific heuristic without diminishing overall performance.

Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza et al.

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-core CPU instead of a GPU. Furthermore, we show that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

Andrei A. Rusu, Sergio Gomez Colmenarejo, Caglar Gulcehre et al.

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance. In this work, we present a novel method called policy distillation that can be used to extract the policy of a reinforcement learning agent and train a new network that performs at the expert level while being dramatically smaller and more efficient. Furthermore, the same method can be used to consolidate multiple task-specific policies into a single policy. We demonstrate these claims using the Atari domain and show that the multi-task distilled agent outperforms the single-task teachers as well as a jointly-trained DQN agent.

Arun Nair, Praveen Srinivasan, Sam Blackwell et al.

We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpassed non-distributed DQN in 41 of the 49 games and also reduced the wall-time required to achieve these results by an order of magnitude on most games.

Jimmy Ba, Volodymyr Mnih, Koray Kavukcuoglu

We present an attention-based model for recognizing multiple objects in images. The proposed model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant regions of the input image. We show that the model learns to both localize and recognize multiple objects despite being given only class labels during training. We evaluate the model on the challenging task of transcribing house number sequences from Google Street View images and show that it is both more accurate than the state-of-the-art convolutional networks and uses fewer parameters and less computation.

Volodymyr Mnih, Nicolas Heess, Alex Graves et al.

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image size. While the model is non-differentiable, it can be trained using reinforcement learning methods to learn task-specific policies. We evaluate our model on several image classification tasks, where it significantly outperforms a convolutional neural network baseline on cluttered images, and on a dynamic visual control problem, where it learns to track a simple object without an explicit training signal for doing so.

Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al.

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.

Volodymyr Mnih, Hugo Larochelle, Geoffrey E. Hinton

Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic models that have recently been applied to a wide range of problems, including collaborative filtering, classification, and modeling motion capture data. While much progress has been made in training non-conditional RBMs, these algorithms are not applicable to conditional models and there has been almost no work on training and generating predictions from conditional RBMs for structured output problems. We first argue that standard Contrastive Divergence-based learning may not be suitable for training CRBMs. We then identify two distinct types of structured output prediction problems and propose an improved learning algorithm for each. The first problem type is one where the output space has arbitrary structure but the set of likely output configurations is relatively small, such as in multi-label classification. The second problem is one where the output space is arbitrarily structured but where the output space variability is much greater, such as in image denoising or pixel labeling. We show that the new learning algorithms can work much better than Contrastive Divergence on both types of problems.