Experimental browser for the Atmosphere
Loading post...
{ "uri": "at://did:plc:fk3wl5kkfeclz4w264m6d3tk/app.bsky.feed.like/3ldrhnocmct2a", "cid": "bafyreicje7yrgo3nvwq55fplwee2qq2cyyyko4jwiauxiislrp2nzj4ohq", "value": { "$type": "app.bsky.feed.like", "subject": { "cid": "bafyreidsol3fhzezu6z6t2rgm4d7cabkaa5gkcgbmlwdklkfgtum4typ24", "uri": "at://did:plc:ku7v5o3u5qysxdiuu3eigpkw/app.bsky.feed.post/3ldq3owasfs2l" }, "createdAt": "2024-12-20T22:45:28.274Z" } }
People use uncertainty to negotiate the explore-exploit trade-off in reinforcement learning. Do they do something similar during mental planning? This is what @haoxuefan.bsky.social, with me and @fredcallaway.bsky.social, has shown: osf.io/preprints/ps...
Dec 20, 2024, 9:38 AM