Papers by Michiaki Tatsubori
Learning Neuro-Symbolic World Models with Conversational Proprioception (2023.acl-short)
Copied to clipboard
| Challenge: | Existing neuro-symbolic approaches to natural language-based interactions are model-free, but there is a need for model-based approaches. |
| Approach: | They propose a model-free approach to learning a logical policy in a text-based game . they use a neural network to enhance the internal logic state with a memory of previous actions . |
| Outcome: | The proposed method can learn neuro-symbolic world models on the TextWorld-Commonsense set of games. |
Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games (2020.emnlp-main)
Copied to clipboard
Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori, Asim Munawar, Ryuki Tachibana
| Challenge: | Reinforcement Learning methods for text-based games fail to generalize on unseen games, especially in small data regimes. |
| Approach: | They propose a Context Relevant Episodic State Truncation method for irrelevant token removal in observation text for improved generalization. |
| Outcome: | The proposed method shows that it can generalize on unseen games using 10x-20x fewer training games compared to previous state-of-the-art methods despite requiring fewer number of training episodes. |
LOA: Logical Optimal Actions for Text-based Interaction Games (2021.acl-demo)
Copied to clipboard
Daiki Kimura, Subhajit Chaudhury, Masaki Ono, Michiaki Tatsubori, Don Joven Agravante, Asim Munawar, Akifumi Wachi, Ryosuke Kohita, Alexander Gray
| Challenge: | et al., 2019) have proposed a neuro-symbolic approach for reinforcement learning in non-simultaneous environments. |
| Approach: | They propose an action decision architecture with a neuro-symbolic framework for natural language interaction games. |
| Outcome: | The proposed framework provides an open-source implementation in Python for the reinforcement learning environment to facilitate an experiment for studying neuro-symbolic agents. |
Language-based General Action Template for Reinforcement Learning Agents (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior knowledge is important in decision-making, and humans preserve it in the form of natural language (NL). |
| Approach: | They propose an environmentagnostic action framework that incorporates prior knowledge into decision-making . they propose to use general semantic schemes to facilitate agent in finding plausible actions . |
| Outcome: | The proposed agent performs better than agents that rely on gamespecific actions. |
Neuro-Symbolic Reinforcement Learning with First-Order Logic (2021.emnlp-main)
Copied to clipboard
Daiki Kimura, Masaki Ono, Subhajit Chaudhury, Ryosuke Kohita, Akifumi Wachi, Don Joven Agravante, Michiaki Tatsubori, Asim Munawar, Alexander Gray
| Challenge: | Existing deep reinforcement learning methods require many trials before convergence and no direct interpretability of trained policies is provided. |
| Approach: | They propose a novel RL method which can learn symbolic and interpretable rules in their differentiable network. |
| Outcome: | The proposed method can learn symbolic and interpretable rules in their differentiable network. |
Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning (2023.acl-long)
Copied to clipboard
Subhajit Chaudhury, Sarathkrishna Swaminathan, Daiki Kimura, Prithviraj Sen, Keerthiram Murugesan, Rosario Uceda-Sosa, Michiaki Tatsubori, Achille Fokoue, Pavan Kapanipathi, Asim Munawar, Alexander Gray
| Challenge: | Existing text-based reinforcement learning agents use embeddings as representations for observation and are fed to an action scorer for predicting the next action. |
| Approach: | They propose a novel neurosymbolic agent that combines a semantic parser and a rule induction system to learn interpretable rules as policies. |
| Outcome: | The proposed method outperforms deep learning-based methods on established text-based game benchmarks on unobserved games and on unseen games. |
DiffG-RL: Leveraging Difference between Environment State and Common Sense (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to solving text-based games require background knowledge as the context is important. |
| Approach: | They propose a novel agent that organizes environment states and common sense by interactive objects with a dedicated graph encoder. |
| Outcome: | The proposed agent outperforms baselines in text-based games by 17% of scores. |
Neuro-Symbolic Approaches for Text-Based Policy Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Text-based games are important testbeds for reinforcement learning in the natural language domain. |
| Approach: | They propose a method that learns interpretable action policy rules from symbolic abstractions of textual observations for improved generalization. |
| Outcome: | The proposed method outperforms existing methods in RL using 5-10x fewer training games. |