Learning to Poke by Poking: Experiential Learning of Intuitive Physics — mentioned by jimfleming

Thu, 21 Mar 2019 15:49:39 GMT

The paper[0] is less vague than the article. To put this in terms of reinforcement learning: 1. Sample actions from a random policy distribution. 2. Fit an inverse model with supervised learning from this data. Inverse models learn to map current observations and next observations to the action which produced the next observation: f(s_t, s_t+1) -> a_t 3. Use reinforcement learning to fit a policy which varies the next observation towards a goal: p(s_t) -> s_t+1 4. Use new data from attempts with the policy and inverse model working together to continue training the inverse model. Motor…

Paper and discussion history. A mention is not an endorsement.

Learning to Poke by Poking: Experiential Learning of Intuitive Physics · HackerPapers discussions

Learning to Poke by Poking: Experiential Learning of Intuitive Physics — mentioned by jimfleming