Learning to Shape Rewards using a Game of Two Partners
David Mguni, Taher Jafferjee, Jianhong Wang, Nicolas Perez-Nieves, Tianpei Yang, Matthew Taylor, Wenbin Song, Feifei Tong, Hui Chen, Jiangcheng Zhu, Jun Wang, Yaodong Yang
Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is time-consuming and error-prone. It also requires domain knowledge which runs contrary to the goal of autonomous learning. We introduce Reinforcement Learning Optimising Shaping Algorithm (ROSA), an automated reward shaping framework in which the shaping-reward function is constructed in a Markov game between two agents. A reward-shaping agent (Shaper) uses switching controls to determine which states to add shaping rewards for more efficient learning while the other agent (Controller) learns the optimal policy for the task using these shaped rewards. We prove that ROSA, which adopts existing RL algorithms, learns to construct a shaping-reward function that is beneficial to the task thus ensuring efficient convergence to high performance policies. We demonstrate ROSA's properties in three didactic experiments and show its superior performance against state-of-the-art RS algorithms in challenging sparse reward environments.
Imperial College London（伦敦帝国理工学院）；Laiye Network Technology Co.Ltd.（来也网络科技有限公司）
Cooperative game is a critical research area in the multi-agent reinforcement learning (MARL). Global reward game is a subclass of cooperative games, where all agents aim to maximize the global reward. Credit assignment is an important problem studied in the global reward game. Most of previous works stood by the view of non-cooperative-game theoretical framework with the shared reward approach, i.e., each agent being assigned a shared global reward directly. This, however, may give each agent an inaccurate reward on its contribution to the group, which could cause inefficient learning. To dea…
While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents to adjust their strategy based on the strategies of those around them. In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time. This setting is challenging because we must infer a new partner's …
Carleton University（卡尔顿大学）；Royal Military College of Canada（加拿大皇家军事学院）
We extend the potential-based shaping method from Markov decision processes to multi-player general-sum stochastic games. We prove that the Nash equilibria in a stochastic game remains unchanged after potential-based shaping is applied to the environment. The property of policy invariance provides a possible way of speeding convergence when learning to play a stochastic game.
We propose a multi-agent distributed reinforcement learning algorithm that balances between potentially conflicting short-term reward and sparse, delayed long-term reward, and learns with partial information in a dynamic environment. We compare different long-term rewards to incentivize the algorithm to maximize individual payoff and overall social welfare. We test the algorithm in two simulated auction games, and demonstrate that 1) our algorithm outperforms two benchmark algorithms in a direct competition, with cost to social welfare, and 2) our algorithm's aggressive competitive behavior ca…
Komatsu University（小松大学）；University of Electro-Communications（电气通信大学）
Artificial intelligence (AI) has achieved superhuman performance in board games such as Go, chess, and Othello (Reversi). In other words, the AI system surpasses the level of a strong human expert player in such games. In this context, it is difficult for a human player to enjoy playing the games with the AI. To keep human players entertained and immersed in a game, the AI is required to dynamically balance its skill with that of the human player. To address this issue, we propose AlphaDDA, an AlphaZero-based AI with dynamic difficulty adjustment (DDA). AlphaDDA consists of a deep neural netwo…
College of Computing & Informatics（计算与信息学院）；Drexel University（德雷塞尔大学）；Google（谷歌）
Training agents using Reinforcement Learning in games with sparse rewards is a challenging problem, since large amounts of exploration are required to retrieve even the first reward. To tackle this problem, a common approach is to use reward shaping to help exploration. However, an important drawback of reward shaping is that agents sometimes learn to optimize the shaped reward instead of the true objective. In this paper, we present a novel technique that we call action guidance that successfully trains agents to eventually optimize the true objective in games with sparse rewards while mainta…
Modern video games are becoming richer and more complex in terms of game mechanics. This complexity allows for the emergence of a wide variety of ways to play the game across the players. From the point of view of the game designer, this means that one needs to anticipate a lot of different ways the game could be played. Machine Learning (ML) could help address this issue. More precisely, Reinforcement Learning is a promising answer to the need of automating video game testing. In this paper we present a video game environment which lets us define multiple play-styles. We then introduce CARI: …
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts of data. Model-based techniques are more data-efficient, but need to acquire explicit knowledge about the environment. In this paper, we take a step towards using model-based techniques in environments with a high-dimensional visual state space by demonstrating t…
The Chinese University of Hong Kong（香港中文大学）；Zhejiang Normal University（浙江师范大学）
Mean field game facilitates analyzing multi-armed bandit (MAB) for a large number of agents by approximating their interactions with an average effect. Existing mean field models for multi-agent MAB mostly assume a binary reward function, which leads to tractable analysis but is usually not applicable in practical scenarios. In this paper, we study the mean field bandit game with a continuous reward function. Specifically, we focus on deriving the existence and uniqueness of mean field equilibrium (MFE), thereby guaranteeing the asymptotic stability of the multi-agent system. To accommodate th…
To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games…
College of Engineering & Informatics, National University of Ireland, Galway（爱尔兰国立大学戈尔韦工程与信息学院）
While reinforcement learning (RL) has been applied to turn-based board games for many years, more complex games involving decision-making in real-time are beginning to receive more attention. A challenge in such environments is that the time that elapses between deciding to take an action and receiving a reward based on its outcome can be longer than the interval between successive decisions. We explore this in the context of a non-player character (NPC) in a modern first-person shooter game. Such games take place in 3D environments where players, both human and computer-controlled, compete by…
Monte Carlo Tree Search (MCTS) methods have proven powerful in planning for sequential decision-making problems such as Go and video games, but their performance can be poor when the planning depth and sampling trajectories are limited or when the rewards are sparse. We present an adaptation of PGRD (policy-gradient for reward-design) for learning a reward-bonus function to improve UCT (a MCTS algorithm). Unlike previous applications of PGRD in which the space of reward-bonus functions was limited to linear functions of hand-coded state-action-features, we use PGRD with a multi-layer convoluti…
Stanford University（斯坦福大学）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
Coordination is often critical to forming prosocial behaviors -- behaviors that increase the overall sum of rewards received by all agents in a multi-agent game. However, state of the art reinforcement learning algorithms often suffer from converging to socially less desirable equilibria when multiple equilibria exist. Previous works address this challenge with explicit reward shaping, which requires the strong assumption that agents can be forced to be prosocial. We propose using a less restrictive peer-rewarding mechanism, gifting, that guides the agents toward more socially desirable equili…
Deep reinforcement learning achieves superhuman performance in a range of video game environments, but requires that a designer manually specify a reward function. It is often easier to provide demonstrations of a target behavior than to design a reward function describing that behavior. Inverse reinforcement learning (IRL) algorithms can infer a reward from demonstrations in low-dimensional continuous control environments, but there has been little work on applying IRL to high-dimensional video games. In our CNN-AIRL baseline, we modify the state-of-the-art adversarial IRL (AIRL) algorithm to…
Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
Department of Electrical and Computer Engineering, Duke University（杜克大学电气与计算机工程系）；Department of Statistics and Data Science, University of Pennsylvania（宾夕法尼亚大学统计与数据科学系）；Department of Biostatistics and Bioinformatics, Duke University（杜克大学生物统计与生物信息学系）；Department of Statistics and Data Science, Yale University（耶鲁大学统计与数据科学系）
University of Michigan（密歇根大学）；Northwestern University（西北大学）；Princeton University（普林斯顿大学）
To achieve sample efficiency in reinforcement learning (RL), it necessitates efficiently exploring the underlying environment. Under the offline setting, addressing the exploration challenge lies in collecting an offline dataset with sufficient coverage. Motivated by such a challenge, we study the reward-free RL problem, where an agent aims to thoroughly explore the environment without any pre-specified reward function. Then, given any extrinsic reward, the agent computes the policy via a planning algorithm with offline data collected in the exploration phase. Moreover, we tackle this problem …
Command and Control Engineering College, Army Engineering University of PLA（中国人民解放军陆军工程大学指挥控制工程学院）；troop of PLA（中国人民解放军31436部队）；Academy of Military Science（军事科学院）
The existing network attack and defense method can be regarded as game, but most of the game only involves network domain, not multiple domain cyberspace. To address this challenge, this paper proposed a multiple domain cyberspace attack and defense game model based on reinforcement learning. We define the multiple domain cyberspace include physical domain, network domain and digital domain. By establishing two agents, representing the attacker and the defender respectively, defender will select the multiple domain actions in the multiple domain cyberspace to obtain defender's optimal reward b…
University of Oslo（奥斯陆大学）；University of Neuchatel（纳沙泰尔大学）；Chalmers University of Technology（查尔姆斯理工大学）
We study the problem of designing autonomous agents that can learn to cooperate effectively with a potentially suboptimal partner while having no access to the joint reward function. This problem is modeled as a cooperative episodic two-agent Markov decision process. We assume control over only the first of the two agents in a Stackelberg formulation of the game, where the second agent is acting so as to maximise expected utility given the first agent's policy. How should the first agent act in order to learn the joint reward function as quickly as possible and so that the joint policy is as c…
We propose the first model-free algorithm that achieves low regret performance for decentralized learning in two-player zero-sum tabular stochastic games with infinite-horizon average-reward objective. In decentralized learning, the learning agent controls only one player and tries to achieve low regret performances against an arbitrary opponent. This contrasts with centralized learning where the agent tries to approximate the Nash equilibrium by controlling both players. In our infinite-horizon undiscounted setting, additional structure assumptions is needed to provide good behaviors of learn…
Reinforcement Learning (RL) is an area of machine learning figuring out how agents take actions in an unknown environment to maximize its rewards. Unlike classical Markov Decision Process (MDP) in which agent has full knowledge of its state, rewards, and transitional probability, reinforcement learning utilizes exploration and exploitation for the model uncertainty. Under the condition that the model usually has a large state space, a neural network (NN) can be used to correlate its input state to its output actions to maximize the agent's rewards. However, building and training an efficient n…
The State-Action-Reward-State-Action Algorithm in Spatial Prisoner's Dilemma Game
College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；Fujian Key Laboratory of Data Science and Statistics, Minnan Normal University（闽南师范大学福建省数据科学与统计重点实验室）
National and Kapodistrian University of Athens（雅典国立卡波季斯特里安大学）
We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states. We also employ variable batch size for training in order to mitigate the loss of the rare reward signal and significantly accelerate training. Despite the large action space due to the number of possible moves, the low-dimensional state space and the rarity of rewards, which only come at the end of a game, DQL is successful in training an agent capable of strong play without the use of any search methods or dom…
OpenAI；UC Berkeley（加州大学伯克利分校）；Univ. of Edinburgh（爱丁堡大学）
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite. Our resul…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Microsoft Research（微软研究院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors, while the policy agent learns to maximize this reward. In imitation learning, near-optimal expert data can be difficult to obtain, and even in the limit of infinite data cannot imply a total ordering over trajectories as preferences can. On the other hand, learning from preferences alone is challenging as a large number of preferences are required to infer a hig…
Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play training strategy is not directly applicable to single-player games. Recently, several practically important combinatorial optimisation problems, such as the travelling salesman problem and the bin packing problem, have been reformulated as reinforcement learning problems, increas…
We present the first reinforcement-learning model to self-improve its reward-modulated training implemented through a continuously improving "intuition" neural network. An agent was trained how to play the arcade video game Pong with two reward-based alternatives, one where the paddle was placed randomly during training, and a second where the paddle was simultaneously trained on three additional neural networks such that it could develop a sense of "certainty" as to how probable its own predicted paddle position will be to return the ball. If the agent was less than 95% certain to return the …
Deep reinforcement learning methods traditionally struggle with tasks where environment rewards are particularly sparse. One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator. However, these demonstrations are typically collected under artificial conditions, i.e. with access to the agent's exact environment setup and the demonstrator's action and reward trajectories. Here we propose a two-stage method that overcomes these limitations by relying on noisy, unaligned footage without access to such data. First, we learn to map una…
In this paper we consider reinforcement learning tasks with progressive rewards; that is, tasks where the rewards tend to increase in magnitude over time. We hypothesise that this property may be problematic for value-based deep reinforcement learning agents, particularly if the agent must first succeed in relatively unrewarding regions of the task in order to reach more rewarding regions. To address this issue, we propose Spectral DQN, which decomposes the reward into frequencies such that the high frequencies only activate when large rewards are found. This allows the training loss to be bal…
We introduce a human-compatible reinforcement-learning approach to a cooperative game, making use of a third-party hand-coded human-compatible bot to generate initial training data and to perform initial evaluation. Our learning approach consists of imitation learning, search, and policy iteration. Our trained agents achieve a new state-of-the-art for bridge bidding in three settings: an agent playing in partnership with a copy of itself; an agent partnering a pre-existing bot; and an agent partnering a human player.
In many problem settings, most notably in game playing, an agent receives a possibly delayed reward for its actions. Often, those rewards are handcrafted and not naturally given. Even simple terminal-only rewards, like winning equals one and losing equals minus one, can not be seen as an unbiased statement, since these values are chosen arbitrarily, and the behavior of the learner may change with different encodings. It is hard to argue about good rewards and the performance of an agent often depends on the design of the reward signal. In particular, in domains where states by nature only have…
Soccer is a sparse rewarding game: any smart or careless action in critical situations can change the result of the match. Therefore players, coaches, and scouts are all curious about the best action to be performed in critical situations, such as the times with a high probability of losing ball possession or scoring a goal. This work proposes a new state representation for the soccer game and a batch reinforcement learning to train a smart policy network. This network gets the contextual information of the situation and proposes the optimal action to maximize the expected goal for the team. W…
While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of {\em reward sparsity}. This is especially true for tasks such as training an agent to play StarCraft II, a real-time strategy game where reward is only given at the end of a game which is usually very long. While this problem can be addressed through reward shaping, such approaches typically require a human expert with specialized knowledge. Inspired by the vis…
We present a computational framework for synthesis of distributed control strategies for a heterogeneous team of robots in a partially observable environment. The goal is to cooperatively satisfy specifications given as Truncated Linear Temporal Logic (TLTL) formulas. Our approach formulates the synthesis problem as a stochastic game and employs a policy graph method to find a control strategy with memory for each agent. We construct the stochastic game on the product between the team transition system and a finite state automaton (FSA) that tracks the satisfaction of the TLTL formula. We use …
