Tags
- action detection 1
- action trajectory constraints 1
- AI assistant 1
- argumentative zoning 1
- Atari-2600 6
- attack poisoning 1
- attention mechanism 1
- causal reasoning 1
- chain of thought 1
- code generation 4
- commonsense learning 1
- compositionality 1
- computer vision 2
- confidence estimation 1
- contrastive learning 2
- data augmentation 2
- dataset 1
- dialogue system 2
- diffusion model 2
- docker 1
- domain modelling 1
- evaluation 1
- exploration strategy 1
- fine tuning 1
- future work 13
- GAN 1
- generalised planning 1
- generative models 2
- GLUE 1
- goal-conditioned reinforcement learning 1
- grounded language learning 2
- hierarchical reinforcement learning 1
- hierarchical RL 3
- hindsight instruction relabeling 1
- IGLU 2
- imitation learning 1
- information retrieval 1
- instruction following 1
- instruction following agent 1
- instruction following robotics with pddl 1
- intrinsic reward 2
- knowledge representation 1
- language agent 1
- language ambiguity 1
- language model 5
- language model reasoning 2
- language reinforcement learning 2
- language reward shaping 2
- large language model 1
- large language models 2
- linear temporal logic 3
- llm 6
- llm agent 2
- llm and pddl 2
- llm cot 1
- llm empirical strategy 1
- llm for reward function 2
- llm hallucination 1
- llm planner 5
- llm planner robotics 1
- llm policy 1
- llm rl 1
- llm verification 1
- llm weak supervision 1
- lm for uncertainty 1
- ltl 1
- machine translation reward model 1
- memory 1
- mixture of experts 1
- model comparison 1
- multimodal 7
- multimodal learning 11
- multitask learning 1
- natural language processing 20
- natural language reinforcement learning 3
- natural language understanding 2
- NetHack 1
- NeurIPS-2021 2
- neuro-symbolic 1
- noisy reward 6
- non-markovian rewards 1
- object detection 1
- offline reinforcement learning 1
- offline RL 1
- open world reasoning 1
- pddl 11
- pddl fixing 1
- pddl repair 1
- pddl3 1
- perturbed rewards 9
- phd thesis plan 2
- planning 3
- planning for dialogue AI 1
- policy gradient 4
- policy sketches 1
- prompt learning 4
- prompting design 1
- python 1
- quality estimation 1
- reinforcement learning 53
- revision 1
- reward design 1
- reward machine 2
- reward model 1
- reward poisoning 5
- rl reward 8
- RNN 1
- robotic arm 1
- robotics 1
- robust reinforcement learning 2
- semantic parsing 2
- sentence embeddings 1
- survey 1
- symbolic planning 1
- theory 1
- training environment 1
- transformer 5
- uncertainty estimation 1
- uncertainty handling 1
- video captioning 1
- visual question answering 1
- width-based planning 2
- world model 1