We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Analyzing the Contribution of Ethical Charters to Building the Future of Artificial Intelligence Governance
Transformers have been shown to be able to 001 perform deductive reasoning on a logical rule-002 base containing rules and statements writte… (see more)n 003 in natural language. Recent works show that 004 such models can also produce the reasoning 005 steps (i.e., the proof graph ) that emulate the 006 model’s logical reasoning process. But these 007 models behave as a black-box unit that emu-008 lates the reasoning process without any causal 009 constraints in the reasoning steps, thus ques-010 tioning the faithfulness. In this work, we frame 011 the deductive logical reasoning task as a causal 012 process by defining three modular components: 013 rule selection, fact selection, and knowledge 014 composition. The rule and fact selection steps 015 select the candidate rule and facts to be used 016 and then the knowledge composition combines 017 them to generate new inferences. This ensures 018 model faithfulness by assured causal relation 019 from the proof step to the inference reasoning. 020 To test our causal reasoning framework, we 021 propose C AUSAL R where the above three com-022 ponents are independently modeled by trans-023 formers. We observe that C AUSAL R is robust 024 to novel language perturbations, and is com-025 petitive with previous works on existing rea-026 soning datasets. Furthermore, the errors made 027 by C AUSAL R are more interpretable due to 028 the multi-modular approach compared to black-029 box generative models. 1 030
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 … (see more)presents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent’s architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 × and improves imitation learning performance on the hardest level from 77% to 90 . 4% . We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
Many real-world applications of reinforcement learning (RL) require the agent to learn from a fixed set of trajectories, without collecting … (see more)new interactions. Policy optimization under this setting is extremely challenging as: 1) the geometry of the objective function is hard to optimize efficiently; 2) the shift of data distributions causes high noise in the value estimation. In this work, we propose a simple yet effective policy iteration approach to batch RL using global optimization techniques known as continuation. By constraining the difference between the learned policy and the behavior policy that generates the fixed trajectories, and continuously relaxing the constraint, our method 1) helps the agent escape local optima; 2) reduces the error in policy evaluation in the optimization procedure. We present results on a variety of control tasks, game environments, and a recommendation task to empirically demonstrate the efficacy of our proposed method.
CAMAP: Artificial neural networks unveil the role of 1 codon arrangement in modulating MHC-I peptides 2 presentation discovery of minor histocompatibility with
30 MHC-I associated peptides (MAPs) play a central role in the elimination of virus-infected and 31 neoplastic cells by CD8 T cells. However… (see more), accurately predicting the MAP repertoire remains 32 difficult, because only a fraction of the transcriptome generates MAPs. In this study, we 33 investigated whether codon arrangement (usage and placement) regulates MAP biogenesis. We 34 developed an artificial neural network called Codon Arrangement MAP Predictor (CAMAP), 35 predicting MAP presentation solely from mRNA sequences flanking the MAP-coding codons 36 (MCCs), while excluding the MCC per se . CAMAP predictions were significantly more accurate 37 when using original codon sequences than shuffled codon sequences which reflect amino acid 38 usage. Furthermore, predictions were independent of mRNA expression and MAP binding affinity 39 to MHC-I molecules and applied to several cell types and species. Combining MAP ligand scores, 40 transcript expression level and CAMAP scores was particularly useful to increaser MAP prediction 41 accuracy. Using an in vitro assay, we showed that varying the synonymous codons in the regions 42 flanking the MCCs (without changing the amino acid sequence) resulted in significant modulation 43 of MAP presentation at the cell surface. Taken together, our results demonstrate the role of codon 44 arrangement in the regulation of MAP presentation and support integration of both translational 45 and post-translational events in predictive algorithms to ameliorate modeling of the 46 immunopeptidome. 47 48 49 they modulated the levels of SIINFEKL presentation in both constructs, but enhanced translation efficiency could only be detected for OVA-RP. These data show that codon arrangement can modulate MAP presentation strength without any changes in the amino
30 MHC-I associated peptides (MAPs) play a central role in the elimination of virus-infected and 31 neoplastic cells by CD8 T cells. However… (see more), accurately predicting the MAP repertoire remains 32 difficult, because only a fraction of the transcriptome generates MAPs. In this study, we 33 investigated whether codon arrangement (usage and placement) regulates MAP biogenesis. We 34 developed an artificial neural network called Codon Arrangement MAP Predictor (CAMAP), 35 predicting MAP presentation solely from mRNA sequences flanking the MAP-coding codons 36 (MCCs), while excluding the MCC per se . CAMAP predictions were significantly more accurate 37 when using original codon sequences than shuffled codon sequences which reflect amino acid 38 usage. Furthermore, predictions were independent of mRNA expression and MAP binding affinity 39 to MHC-I molecules and applied to several cell types and species. Combining MAP ligand scores, 40 transcript expression level and CAMAP scores was particularly useful to increaser MAP prediction 41 accuracy. Using an in vitro assay, we showed that varying the synonymous codons in the regions 42 flanking the MCCs (without changing the amino acid sequence) resulted in significant modulation 43 of MAP presentation at the cell surface. Taken together, our results demonstrate the role of codon 44 arrangement in the regulation of MAP presentation and support integration of both translational 45 and post-translational events in predictive algorithms to ameliorate modeling of the 46 immunopeptidome. 47 48 49 they modulated the levels of SIINFEKL presentation in both constructs, but enhanced translation efficiency could only be detected for OVA-RP. These data show that codon arrangement can modulate MAP presentation strength without any changes in the amino
Lethal autonomous weapon systems (LAWS, ethal autonomous weapon also known as killer robots) are a real and emerging technology that have th… (see more)e potential to radically transform warfare. Because of the myriad of moral, legal, privacy, and security risks the technology introduces, many scholars and advocates have called for a ban on the development, production, and use of fully autonomous weapons [1], [2].
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during plan… (see more)ning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by attending to the relevant objects, leading to better out-of-distribution generalization performance.
In this paper, we investigate the problem of system identification for autonomous switched linear systems with complete state observations.… (see more) We propose switched least squares method for the identification for switched linear systems, show that this method is strongly consistent, and derive data-dependent and data-independent rates of convergence. In particular, our data-dependent rate of convergence shows that, almost surely, the system identification error is O (cid:0)(cid:112) log( T ) /T (cid:1) where T is the time horizon. These results show that our method for switched linear systems has the same rate of convergence as least squares method for non-switched linear systems. We compare our results with those in the literature. We present numerical examples to illustrate the performance of the proposed system identification method.
Modularity is a compelling solution to continual learning (CL), the problem of modeling sequences of related tasks. Learning and then compos… (see more)ing modules to solve different tasks provides an abstraction to address the principal challenges of CL including catastrophic forgetting, backward and forward transfer across tasks, and sub-linear model growth. We introduce local module composition (LMC), an approach to modular CL where each module is provided a local structural component that estimates a module's relevance to the input. Dynamic module composition is performed layer-wise based on local relevance scores. We demonstrate that agnosticity to task identities (IDs) arises from (local) structural learning that is module-specific as opposed to the task- and/or model-specific as in previous works, making LMC applicable to more CL settings compared to previous works. In addition, LMC also tracks statistics about the input distribution and adds new modules when outlier samples are detected. In the first set of experiments, LMC performs favorably compared to existing methods on the recent Continual Transfer-learning Benchmark without requiring task identities. In another study, we show that the locality of structural learning allows LMC to interpolate to related but unseen tasks (OOD), as well as to compose modular networks trained independently on different task sequences into a third modular network without any fine-tuning. Finally, in search for limitations of LMC we study it on more challenging sequences of 30 and 100 tasks, demonstrating that local module selection becomes much more challenging in presence of a large number of candidate modules. In this setting best performing LMC spawns much fewer modules compared to an oracle based baseline, however, it reaches a lower overall accuracy. The codebase is available under https://github.com/oleksost/LMC.
Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generali… (see more)zation, we incorporate the inherent sequential structure in reinforcement learning into the representation learning process. This approach is orthogonal to recent approaches, which rarely exploit this structure explicitly. Specifically, we introduce a theoretically motivated policy similarity metric (PSM) for measuring behavioral similarity between states. PSM assigns high similarity to states for which the optimal policies in those states as well as in future states are similar. We also present a contrastive representation learning procedure to embed any state similarity metric, which we instantiate with PSM to obtain policy similarity embeddings (PSEs). We demonstrate that PSEs improve generalization on diverse benchmarks, including LQR with spurious correlations, a jumping task from pixels, and Distracting DM Control Suite.
