United Kingdom

One of the key issues for imitation learning lies in making policy learned from limited samples to generalize well in the whole state-action space. This problem is much more severe in high-dimensional state environments, such as game playing with raw pixel inputs. Under this situation, even state-of-the-art adversary-based imitation learning algorithms fail. Through empirical studies, we find that the main cause lies in the failure of training a powerful discriminator to generate meaningful rewards in high-dimensional environments. Although it seems that dimensionality reduction can help, a straightforward application of off-the-shelf methods cannot achieve good performance. In this work, we show in theory that the balance between dimensionality reduction and discriminative training is essential for effective learning. To achieve this target, we propose HashReward, which utilizes the idea of supervised hashing to realize such an ideal balance. Experimental results show that HashReward could outperform state-of-the-art methods for a large gap under the challenging high-dimensional environments.

AAMAS 2021

Imitation Learning from Pixel-Level Demonstrations by HashReward

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://assets.underline.io/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

technical paper

Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating new challenging tasks for agents to adapt to, thereby facilitating the acquisition of new skills. In order to extend MARL methods to real-world domains outside of video games, we envision in this blue sky paper that maintaining a diversity-aware auto-curriculum is critical for successful MARL applications. Specifically, we argue that <i>behavioural diversity</i> is a pivotal, yet under-explored, component for real-world multiagent learning systems, and that significant work remains in understanding how to design a diversity-aware auto-curriculum. We list four open challenges for auto-curriculum techniques, which we believe deserve more attention from this community. Towards validating our vision, we recommend modelling realistic interactive behaviours in autonomous driving as an important test bed, and recommend the SMARTS/ULTRA benchmark.

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems (Blue Sky Ideas Track)

The real world is awash with multi-agent problems that require collective action by self-interested agents, from the routing of packets across a computer network to the management of irrigation systems. Such systems have local incentives for individuals, whose behavior has an impact on the global outcome for the group. Given appropriate mechanisms describing agent interaction, groups may achieve socially beneficial outcomes, even in the face of short-term selfish incentives. In many cases, collective action problems possess an underlying graph structure, whose topology crucially determines the relationship between local decisions and emergent global effects. Such scenarios have received great attention through the lens of network games. However, this abstraction typically collapses important dimensions, such as geometry and time, relevant to the design of mechanisms promoting cooperation. In parallel work, multi-agent deep reinforcement learning has shown great promise in modelling the emergence of self-organized cooperation in complex gridworld domains. Here we apply this paradigm in graph-structured collective action problems.

Modelling Cooperation in Network Games with Spatio-Temporal Complexity

Participatory Budgeting processes are usually designed to span several years, with referenda for new budget allocations taking place regularly. This paper presents the first formalization of long-term PB. We introduce a theory of fairness for this setting, investigate under which conditions our fairness criteria can be satisfied, and analyze the computational complexity of verifying them.

Fairness in Long-Term Participatory Budgeting

Pay-per-last-$N$-shares'' (PPLNS) is one of the most common payout strategies used by mining pools in Proof-of-Work (PoW) cryptocurrencies such as Bitcoin.As with any payment scheme, it is imperative to study issues of incentive compatibility of miners within the pool. For PPLNS this question has only been partially answered; we know that reasonably-sized miners within a PPLNS pool prefer following the pool protocol over employing {\em specific} deviations. In this paper, we present a novel modification to PPLNS where we randomise the protocol in a natural way. We call our protocol ''Randomised pay-per-last-$N$-shares'' (RPPLNS), and note that the randomised structure of the protocol greatly simplifies the study of its incentive compatibility. We show that RPPLNS maintains the strengths of PPLNS (i.e., fairness, variance reduction, and resistance to pool hopping), while also being robust against a richer class of strategic mining than what has been shown for PPLNS.

RPPLNS: Pay-per-last-N-shares with a Randomised Twist

Trading mechanisms play a fundamental role in the health of financial markets. For example, it is believed that continuous double auctions constitute fertile soil for predatory behaviour and toxic order flows. To this end, frequent call markets have been proposed as an alternative design choice to address the latency arbitrage opportunities built in those markets. This paper studies the extent to which adaptive rules to define the length of the clearing intervals affect the performance of frequent call markets.

Call Markets with Adaptive Clearing Intervals

Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this paper, we investigate the potential of agent learning from trainers' facial expressions via interpreting them as evaluative feedback. To do so, we implemented TAMER which is a popular interactive reinforcement learning method in a reinforcement-learning benchmark problem    Infinite Mario, and conducted the first large-scale study of TAMER involving 561 participants. With designed CNN-RNN model, our analysis shows that telling trainers to use facial expressions and competition can improve the accuracies for estimating positive and negative feedback using facial expressions. In addition, our results with a simulation experiment show that learning solely from predicted feedback based on facial expressions is possible and using strong/effective prediction models or a regression method, facial responses would significantly improve the performance of agents. Furthermore, our experiment supports previous studies demonstrating the importance of bi-directional feedback and competitive elements in the training interface.

Facial Feedback for Reinforcement Learning: A Case Study and Offline Analysis Using the TAMER Framework (JAAMAS Track)

Action advising is a peer-to-peer knowledge exchange technique built on the teacher-student paradigm to alleviate the sample inefficiency problem in deep reinforcement learning. Recently proposed student-initiated approaches have obtained promising results. However, due to being in the early stages of development, these also have some substantial shortcomings. One of the abilities that are absent in the current methods is further utilising advice by reusing, which is especially crucial in the practical settings considering the budget constraints in peer-to-peer interactions. In this study, we present an approach to enable the student agent to imitate previously acquired advice to reuse them directly in its exploration policy, without any interventions in the learning mechanism itself. In particular, we employ a behavioural cloning module to imitate the teacher policy and use dropout regularisation to have a notion of epistemic uncertainty to keep track of which state-advice pairs are actually collected. As the results of experiments we conducted in three Atari games show, advice reusing via imitation is indeed a feasible option in deep RL and our approach can successfully achieve this while significantly improving the learning performance, even when it is paired with a simple early advising heuristic.

Action Advising with Advice Imitation in Deep Reinforcement Learning

We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC) that adopts supervised learning followed by the problem of compounding error, previous solutions like inverse reinforcement learning (IRL) and recent generative adversarial methods involve a bi-level or alternating optimization for updating the reward function and the policy, suffering from high computational cost and training instability. Inspired by recent progress in energy-based model (EBM), in this paper, we propose a simplified IL framework named Energy-Based Imitation Learning (EBIL). Instead of updating the reward and policy iteratively, EBIL breaks out of the traditional IRL paradigm by a simple and flexible two-stage solution: first estimating the expert energy as the surrogate reward function through score matching, then utilizing such a reward for learning the policy by reinforcement learning algorithms. EBIL combines the idea of both EBM and occupancy measure matching, and via theoretic analysis we reveal that EBIL and Max-Entropy IRL (MaxEnt IRL) approaches are two sides of the same coin, and thus EBIL could be an alternative of adversarial IRL methods. Extensive experiments on qualitative and quantitative evaluations indicate that EBIL is able to recover meaningful and interpretative reward signals while achieving effective and comparable performance against existing algorithms on IL benchmarks.

Energy-Based Imitation Learning

Evolutionary strategies (ES) and off-policy learning algorithms are two major workhorses of Reinforcement learning (RL): ES adopt a simple blackbox approach to optimization but it can be slightly more sample inefficient; off-policy learning is by design more sample efficient but the updates can be unstable. Motivated by their trade-offs, we propose CEM-ACER, a combination of Cross-entropy method, a standard ES algorithm, and Actor-critic with experience replay (ACER), an off-policy actor-critic algorithm. Our proposal relies on a key insight: off-policy algorithms provide a natural mechanism to efficiently evolve parameter populations as part of an ES algorithm. Across a wide range of benchmark control tasks, we show that CEM-ACER balances the strengths of CEM and ACER, leading to an algorithm that consistently outperforms its individual building blocks, as well as other competitive baseline algorithms.

Guiding Evolutionary Strategies with Off-Policy Actor-Critic

Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments. Unlike cooperative environments where agents strive towards a common goal, mixed environments are notorious for the conflicts of selfish and social interests. As a consequence, purely rational agents often struggle to maintain cooperation. A prevalent approach to induce cooperative behaviour is to assign additional rewards based on other agents' well-being. However, this approach suffers from the issue of multi-agent credit assignment, which can hinder performance. This issue is efficiently alleviated in cooperative setting with such state-of-the-art algorithms as QMIX and COMA. Still, when applied to mixed environments, these algorithms may result in unfair allocation of rewards. We propose BAROCCO, an extension of these algorithms capable to balance individual and social incentives. The mechanism behind BAROCCO is to train two distinct but interwoven components that jointly affect agents' decisions. We experimentally confirm the advantages of BAROCCO.

Downloads

Next from AAMAS 2021

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems (Blue Sky Ideas Track)

Similar lecture

Towards Sample Efficient Learners in Population based Referential Games through Action Advising

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2021

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems (Blue Sky Ideas Track)

Similar lecture

Towards Sample Efficient Learners in Population based Referential Games through Action Advising

Downloads