Beth's Blog: How Nonprofits Can Use Social Media

FEBRUARY 18, 2014

There are two different methods to evaluate your training. Alternately, you may feel so good about it and say my job is done. Use Learning Theory. It defines the outcomes of training in four different areas that you can measure. to define the four levels of training evaluation. The four levels are: Reaction.

Evaluation 131

Evaluation Train Training Tips 131

Beth's Blog: How Nonprofits Can Use Social Media

JANUARY 27, 2014

Designing and delivering a training to a nonprofit audience is not about extreme content delivery or putting together a PowerPoint and answering questions. If you want to get results, you need to think about instructional design and learning theory. And, there is no shortage of learning theories and research.

Instructional Design 113

Instructional Design Instruction Instructional Train 113

The AI Alignment Forum

FEBRUARY 28, 2025

Defining the Theoretical Reward Learning Research Agenda In one sentence, the aim of this research agenda is to develop a mature theoretical foundation for the field of reward learning (and relevant adjacent areas). Some other notable options include e.g. multi-objective RL, temporal logic, or different kinds of non-Markovian rewards.

Research 40

Research Learning Method Policy 40

Google Research AI blog

APRIL 30, 2023

This year we are presenting over 100 papers and are actively involved in organizing and hosting a number of different events, including workshops and interactive sessions.

Google 105

Google Language Model Jing 105

Museum 2.0

SEPTEMBER 26, 2012

We attentively respond to requests and purposefully use different modes of feedback to inform program design from our comment board, social media outlets, conversations and observations both inside and outside the museum, creative feedback at events such as our Show and Tell Booth and online visitor surveys specific to our programs.

Museum 49

Museum Program Community Participatory 49

The AI Alignment Forum

FEBRUARY 28, 2025

Alternatively, see the main paper. The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret In this paper , we look at what happens when a learnt reward function is optimised. This paper is discussed in more detail in this post. In this sense, it is similar to the first part of this sequence.

Learning 40

Learning Discussion Classes Policy 40

The AI Alignment Forum

FEBRUARY 7, 2025

We link to hundreds of papers and blog posts and offer approximately a hundred different example projects. Alternatives to adversarial training : Adversarial training (and the rest of todays best alignment techniques) have failed to create LLM agents that reliably avoid misaligned goals. Kumar et al. , Wen et al. , and Bhatt et al.

Research 52

Research Fund Open Technique 52